Compare commits
2 Commits
v0.2.46
...
perf/pipel
| Author | SHA1 | Date | |
|---|---|---|---|
|
eb9ec687cb | ||
|
|
d297540053 |
@@ -1,402 +0,0 @@
|
||||
name: Build Sidecars
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths: ['python/**']
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
bump-sidecar-version:
|
||||
name: Bump sidecar version and tag
|
||||
if: "!contains(github.event.head_commit.message, '[skip ci]')"
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
version: ${{ steps.bump.outputs.version }}
|
||||
tag: ${{ steps.bump.outputs.tag }}
|
||||
has_changes: ${{ steps.check_changes.outputs.has_changes }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 2
|
||||
|
||||
- name: Check for python changes
|
||||
id: check_changes
|
||||
run: |
|
||||
# If triggered by workflow_dispatch, always build
|
||||
if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
|
||||
echo "has_changes=true" >> $GITHUB_OUTPUT
|
||||
exit 0
|
||||
fi
|
||||
# Check if any python/ files changed in this commit
|
||||
CHANGED=$(git diff --name-only HEAD~1 HEAD -- python/ 2>/dev/null || echo "")
|
||||
if [ -n "$CHANGED" ]; then
|
||||
echo "has_changes=true" >> $GITHUB_OUTPUT
|
||||
echo "Python changes detected: $CHANGED"
|
||||
else
|
||||
echo "has_changes=false" >> $GITHUB_OUTPUT
|
||||
echo "No python/ changes detected, skipping sidecar build"
|
||||
fi
|
||||
|
||||
- name: Configure git
|
||||
if: steps.check_changes.outputs.has_changes == 'true'
|
||||
run: |
|
||||
git config user.name "Gitea Actions"
|
||||
git config user.email "actions@gitea.local"
|
||||
|
||||
- name: Bump sidecar patch version
|
||||
if: steps.check_changes.outputs.has_changes == 'true'
|
||||
id: bump
|
||||
run: |
|
||||
# Read current version from python/pyproject.toml
|
||||
CURRENT=$(grep '^version = ' python/pyproject.toml | head -1 | sed 's/version = "\(.*\)"/\1/')
|
||||
echo "Current sidecar version: ${CURRENT}"
|
||||
|
||||
# Increment patch number
|
||||
MAJOR=$(echo "${CURRENT}" | cut -d. -f1)
|
||||
MINOR=$(echo "${CURRENT}" | cut -d. -f2)
|
||||
PATCH=$(echo "${CURRENT}" | cut -d. -f3)
|
||||
NEW_PATCH=$((PATCH + 1))
|
||||
NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
|
||||
echo "New sidecar version: ${NEW_VERSION}"
|
||||
|
||||
# Update python/pyproject.toml
|
||||
sed -i "s/^version = \"${CURRENT}\"/version = \"${NEW_VERSION}\"/" python/pyproject.toml
|
||||
|
||||
echo "version=${NEW_VERSION}" >> $GITHUB_OUTPUT
|
||||
echo "tag=sidecar-v${NEW_VERSION}" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Commit and tag
|
||||
if: steps.check_changes.outputs.has_changes == 'true'
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
NEW_VERSION="${{ steps.bump.outputs.version }}"
|
||||
TAG="${{ steps.bump.outputs.tag }}"
|
||||
git add python/pyproject.toml
|
||||
git commit -m "chore: bump sidecar version to ${NEW_VERSION} [skip ci]"
|
||||
git tag "${TAG}"
|
||||
|
||||
# Push using token for authentication (rebase in case another workflow pushed first)
|
||||
REMOTE_URL=$(git remote get-url origin | sed "s|://|://gitea-actions:${BUILD_TOKEN}@|")
|
||||
git pull --rebase "${REMOTE_URL}" main || true
|
||||
git push "${REMOTE_URL}" HEAD:main
|
||||
git push "${REMOTE_URL}" "${TAG}"
|
||||
|
||||
- name: Create Gitea release
|
||||
if: steps.check_changes.outputs.has_changes == 'true'
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
TAG="${{ steps.bump.outputs.tag }}"
|
||||
VERSION="${{ steps.bump.outputs.version }}"
|
||||
RELEASE_NAME="Sidecar v${VERSION}"
|
||||
|
||||
curl -s -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"tag_name\": \"${TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated sidecar build.\", \"draft\": false, \"prerelease\": false}" \
|
||||
"${REPO_API}/releases"
|
||||
echo "Created release: ${RELEASE_NAME}"
|
||||
|
||||
build-sidecar-linux:
|
||||
name: Build Sidecar (Linux)
|
||||
needs: bump-sidecar-version
|
||||
if: needs.bump-sidecar-version.outputs.has_changes == 'true'
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
PYTHON_VERSION: "3.11"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ needs.bump-sidecar-version.outputs.tag }}
|
||||
|
||||
- name: Install uv
|
||||
run: |
|
||||
if command -v uv &> /dev/null; then
|
||||
echo "uv already installed: $(uv --version)"
|
||||
else
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
echo "$HOME/.local/bin" >> $GITHUB_PATH
|
||||
fi
|
||||
|
||||
- name: Install ffmpeg
|
||||
run: sudo apt-get update && sudo apt-get install -y ffmpeg
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Build sidecar (CUDA)
|
||||
working-directory: python
|
||||
run: uv run --python ${{ env.PYTHON_VERSION }} python build_sidecar.py --with-cuda
|
||||
|
||||
- name: Package sidecar (CUDA)
|
||||
run: |
|
||||
cd python/dist/voice-to-notes-sidecar && zip -r ../../../sidecar-linux-x86_64-cuda.zip .
|
||||
|
||||
- name: Build sidecar (CPU)
|
||||
working-directory: python
|
||||
run: |
|
||||
rm -rf dist/voice-to-notes-sidecar
|
||||
uv run --python ${{ env.PYTHON_VERSION }} python build_sidecar.py --cpu-only
|
||||
|
||||
- name: Package sidecar (CPU)
|
||||
run: |
|
||||
cd python/dist/voice-to-notes-sidecar && zip -r ../../../sidecar-linux-x86_64-cpu.zip .
|
||||
|
||||
- name: Upload to sidecar release
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
sudo apt-get install -y jq
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
TAG="${{ needs.bump-sidecar-version.outputs.tag }}"
|
||||
|
||||
# Find the sidecar release by tag (retry up to 30 times with 10s delay)
|
||||
echo "Waiting for sidecar release ${TAG} to be available..."
|
||||
for i in $(seq 1 30); do
|
||||
RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/tags/${TAG}")
|
||||
RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
|
||||
|
||||
if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
|
||||
echo "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
|
||||
break
|
||||
fi
|
||||
|
||||
echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
|
||||
sleep 10
|
||||
done
|
||||
|
||||
if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
|
||||
echo "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for file in sidecar-*.zip; do
|
||||
filename=$(basename "$file")
|
||||
encoded_name=$(echo "$filename" | sed 's/ /%20/g')
|
||||
echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
|
||||
|
||||
ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
|
||||
if [ -n "${ASSET_ID}" ]; then
|
||||
curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
|
||||
fi
|
||||
|
||||
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/octet-stream" \
|
||||
-T "$file" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
|
||||
echo "Upload response: HTTP ${HTTP_CODE}"
|
||||
done
|
||||
|
||||
build-sidecar-windows:
|
||||
name: Build Sidecar (Windows)
|
||||
needs: bump-sidecar-version
|
||||
if: needs.bump-sidecar-version.outputs.has_changes == 'true'
|
||||
runs-on: windows-latest
|
||||
env:
|
||||
PYTHON_VERSION: "3.11"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ needs.bump-sidecar-version.outputs.tag }}
|
||||
|
||||
- name: Install uv
|
||||
shell: powershell
|
||||
run: |
|
||||
if (Get-Command uv -ErrorAction SilentlyContinue) {
|
||||
Write-Host "uv already installed: $(uv --version)"
|
||||
} else {
|
||||
irm https://astral.sh/uv/install.ps1 | iex
|
||||
echo "$env:USERPROFILE\.local\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
}
|
||||
|
||||
- name: Install ffmpeg
|
||||
shell: powershell
|
||||
run: choco install ffmpeg -y
|
||||
|
||||
- name: Set up Python
|
||||
shell: powershell
|
||||
run: uv python install ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install 7-Zip
|
||||
shell: powershell
|
||||
run: |
|
||||
if (-not (Get-Command 7z -ErrorAction SilentlyContinue)) {
|
||||
choco install 7zip -y
|
||||
}
|
||||
|
||||
- name: Build sidecar (CUDA)
|
||||
shell: powershell
|
||||
working-directory: python
|
||||
run: uv run --python ${{ env.PYTHON_VERSION }} python build_sidecar.py --with-cuda
|
||||
|
||||
- name: Package sidecar (CUDA)
|
||||
shell: powershell
|
||||
run: |
|
||||
7z a -tzip -mx=5 sidecar-windows-x86_64-cuda.zip .\python\dist\voice-to-notes-sidecar\*
|
||||
|
||||
- name: Build sidecar (CPU)
|
||||
shell: powershell
|
||||
working-directory: python
|
||||
run: |
|
||||
Remove-Item -Recurse -Force dist\voice-to-notes-sidecar
|
||||
uv run --python ${{ env.PYTHON_VERSION }} python build_sidecar.py --cpu-only
|
||||
|
||||
- name: Package sidecar (CPU)
|
||||
shell: powershell
|
||||
run: |
|
||||
7z a -tzip -mx=5 sidecar-windows-x86_64-cpu.zip .\python\dist\voice-to-notes-sidecar\*
|
||||
|
||||
- name: Upload to sidecar release
|
||||
shell: powershell
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
$REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
|
||||
$Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
|
||||
$TAG = "${{ needs.bump-sidecar-version.outputs.tag }}"
|
||||
|
||||
# Find the sidecar release by tag (retry up to 30 times with 10s delay)
|
||||
Write-Host "Waiting for sidecar release ${TAG} to be available..."
|
||||
$RELEASE_ID = $null
|
||||
|
||||
for ($i = 1; $i -le 30; $i++) {
|
||||
try {
|
||||
$release = Invoke-RestMethod -Uri "${REPO_API}/releases/tags/${TAG}" -Headers $Headers -ErrorAction Stop
|
||||
$RELEASE_ID = $release.id
|
||||
|
||||
if ($RELEASE_ID) {
|
||||
Write-Host "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
|
||||
break
|
||||
}
|
||||
} catch {
|
||||
# Release not ready yet
|
||||
}
|
||||
|
||||
Write-Host "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
|
||||
Start-Sleep -Seconds 10
|
||||
}
|
||||
|
||||
if (-not $RELEASE_ID) {
|
||||
Write-Host "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
|
||||
exit 1
|
||||
}
|
||||
|
||||
Get-ChildItem -Path . -Filter "sidecar-*.zip" | ForEach-Object {
|
||||
$filename = $_.Name
|
||||
$encodedName = [System.Uri]::EscapeDataString($filename)
|
||||
$size = [math]::Round($_.Length / 1MB, 1)
|
||||
Write-Host "Uploading ${filename} (${size} MB)..."
|
||||
|
||||
try {
|
||||
$assets = Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets" -Headers $Headers
|
||||
$existing = $assets | Where-Object { $_.name -eq $filename }
|
||||
if ($existing) {
|
||||
Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets/$($existing.id)" -Method Delete -Headers $Headers
|
||||
}
|
||||
} catch {}
|
||||
|
||||
$uploadUrl = "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encodedName}"
|
||||
$result = curl.exe --fail --silent --show-error `
|
||||
-X POST `
|
||||
-H "Authorization: token $env:BUILD_TOKEN" `
|
||||
-H "Content-Type: application/octet-stream" `
|
||||
-T "$($_.FullName)" `
|
||||
"$uploadUrl" 2>&1
|
||||
if ($LASTEXITCODE -eq 0) {
|
||||
Write-Host "Upload successful: ${filename}"
|
||||
} else {
|
||||
Write-Host "WARNING: Upload failed for ${filename}: ${result}"
|
||||
}
|
||||
}
|
||||
|
||||
build-sidecar-macos:
|
||||
name: Build Sidecar (macOS)
|
||||
needs: bump-sidecar-version
|
||||
if: needs.bump-sidecar-version.outputs.has_changes == 'true'
|
||||
runs-on: macos-latest
|
||||
env:
|
||||
PYTHON_VERSION: "3.11"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ needs.bump-sidecar-version.outputs.tag }}
|
||||
|
||||
- name: Install uv
|
||||
run: |
|
||||
if command -v uv &> /dev/null; then
|
||||
echo "uv already installed: $(uv --version)"
|
||||
else
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
echo "$HOME/.local/bin" >> $GITHUB_PATH
|
||||
fi
|
||||
|
||||
- name: Install ffmpeg
|
||||
run: brew install ffmpeg
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Build sidecar (CPU)
|
||||
working-directory: python
|
||||
run: uv run --python ${{ env.PYTHON_VERSION }} python build_sidecar.py --cpu-only
|
||||
|
||||
- name: Package sidecar (CPU)
|
||||
run: |
|
||||
cd python/dist/voice-to-notes-sidecar && zip -r ../../../sidecar-macos-aarch64-cpu.zip .
|
||||
|
||||
- name: Upload to sidecar release
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
which jq || brew install jq
|
||||
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
TAG="${{ needs.bump-sidecar-version.outputs.tag }}"
|
||||
|
||||
# Find the sidecar release by tag (retry up to 30 times with 10s delay)
|
||||
echo "Waiting for sidecar release ${TAG} to be available..."
|
||||
for i in $(seq 1 30); do
|
||||
RELEASE_JSON=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/tags/${TAG}")
|
||||
RELEASE_ID=$(echo "$RELEASE_JSON" | jq -r '.id // empty')
|
||||
|
||||
if [ -n "${RELEASE_ID}" ] && [ "${RELEASE_ID}" != "null" ]; then
|
||||
echo "Found sidecar release: ${TAG} (ID: ${RELEASE_ID})"
|
||||
break
|
||||
fi
|
||||
|
||||
echo "Attempt ${i}/30: Release not ready yet, retrying in 10s..."
|
||||
sleep 10
|
||||
done
|
||||
|
||||
if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
|
||||
echo "ERROR: Failed to find sidecar release for tag ${TAG} after 30 attempts."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for file in sidecar-*.zip; do
|
||||
filename=$(basename "$file")
|
||||
encoded_name=$(echo "$filename" | sed 's/ /%20/g')
|
||||
echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
|
||||
|
||||
ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
|
||||
if [ -n "${ASSET_ID}" ]; then
|
||||
curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
|
||||
fi
|
||||
|
||||
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/octet-stream" \
|
||||
-T "$file" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
|
||||
echo "Upload response: HTTP ${HTTP_CODE}"
|
||||
done
|
||||
191
.gitea/workflows/build.yml
Normal file
191
.gitea/workflows/build.yml
Normal file
@@ -0,0 +1,191 @@
|
||||
name: Build & Release
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
tags: ["v*"]
|
||||
pull_request:
|
||||
branches: [main]
|
||||
|
||||
env:
|
||||
PYTHON_VERSION: "3.11"
|
||||
NODE_VERSION: "20"
|
||||
|
||||
jobs:
|
||||
build-sidecar:
|
||||
name: Build sidecar (${{ matrix.target }})
|
||||
runs-on: ${{ matrix.runner }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- runner: ubuntu-latest
|
||||
target: x86_64-unknown-linux-gnu
|
||||
platform: linux
|
||||
- runner: windows-latest
|
||||
target: x86_64-pc-windows-msvc
|
||||
platform: windows
|
||||
- runner: macos-latest
|
||||
target: aarch64-apple-darwin
|
||||
platform: macos
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Build sidecar
|
||||
working-directory: python
|
||||
run: uv run --python ${{ env.PYTHON_VERSION }} python build_sidecar.py --cpu-only
|
||||
|
||||
- name: Upload sidecar artifact
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: sidecar-${{ matrix.target }}
|
||||
path: python/dist/voice-to-notes-sidecar/
|
||||
retention-days: 7
|
||||
|
||||
build-tauri:
|
||||
name: Build app (${{ matrix.target }})
|
||||
needs: build-sidecar
|
||||
runs-on: ${{ matrix.runner }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- runner: ubuntu-latest
|
||||
target: x86_64-unknown-linux-gnu
|
||||
platform: linux
|
||||
- runner: windows-latest
|
||||
target: x86_64-pc-windows-msvc
|
||||
platform: windows
|
||||
- runner: macos-latest
|
||||
target: aarch64-apple-darwin
|
||||
platform: macos
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
|
||||
- name: Install Rust stable
|
||||
uses: dtolnay/rust-toolchain@stable
|
||||
|
||||
- name: Install system dependencies (Linux)
|
||||
if: matrix.platform == 'linux'
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf
|
||||
|
||||
- name: Install system dependencies (macOS)
|
||||
if: matrix.platform == 'macos'
|
||||
run: |
|
||||
brew install --quiet create-dmg || true
|
||||
|
||||
- name: Download sidecar artifact
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
name: sidecar-${{ matrix.target }}
|
||||
path: src-tauri/binaries/
|
||||
|
||||
- name: Make sidecar executable (Unix)
|
||||
if: matrix.platform != 'windows'
|
||||
run: chmod +x src-tauri/binaries/voice-to-notes-sidecar-${{ matrix.target }}
|
||||
|
||||
- name: Install npm dependencies
|
||||
run: npm ci
|
||||
|
||||
- name: Build Tauri app
|
||||
run: npm run tauri build
|
||||
env:
|
||||
TAURI_SIGNING_PRIVATE_KEY: ${{ secrets.TAURI_SIGNING_PRIVATE_KEY }}
|
||||
TAURI_CONFIG: '{"bundle":{"externalBin":["binaries/voice-to-notes-sidecar"]}}'
|
||||
|
||||
- name: Upload app artifacts (Linux)
|
||||
if: matrix.platform == 'linux'
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: app-${{ matrix.target }}
|
||||
path: |
|
||||
src-tauri/target/release/bundle/deb/*.deb
|
||||
src-tauri/target/release/bundle/appimage/*.AppImage
|
||||
retention-days: 30
|
||||
|
||||
- name: Upload app artifacts (Windows)
|
||||
if: matrix.platform == 'windows'
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: app-${{ matrix.target }}
|
||||
path: |
|
||||
src-tauri/target/release/bundle/msi/*.msi
|
||||
src-tauri/target/release/bundle/nsis/*.exe
|
||||
retention-days: 30
|
||||
|
||||
- name: Upload app artifacts (macOS)
|
||||
if: matrix.platform == 'macos'
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: app-${{ matrix.target }}
|
||||
path: |
|
||||
src-tauri/target/release/bundle/dmg/*.dmg
|
||||
src-tauri/target/release/bundle/macos/*.app
|
||||
retention-days: 30
|
||||
|
||||
release:
|
||||
name: Create Release
|
||||
needs: build-tauri
|
||||
if: github.ref == 'refs/heads/main'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install required tools
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y jq curl
|
||||
|
||||
- name: Download all app artifacts
|
||||
uses: actions/download-artifact@v3
|
||||
with:
|
||||
path: artifacts/
|
||||
|
||||
- name: Generate release tag
|
||||
id: tag
|
||||
run: echo "tag=build-$(date +%Y%m%d-%H%M%S)" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Create release
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
TAG: ${{ steps.tag.outputs.tag }}
|
||||
run: |
|
||||
# Create the release
|
||||
RELEASE_ID=$(curl -s -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"tag_name\": \"${TAG}\", \"name\": \"Voice to Notes ${TAG}\", \"body\": \"Automated build from main branch.\", \"draft\": false, \"prerelease\": true}" \
|
||||
"${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}/releases" | jq -r '.id')
|
||||
|
||||
echo "Release ID: ${RELEASE_ID}"
|
||||
|
||||
if [ "${RELEASE_ID}" = "null" ] || [ -z "${RELEASE_ID}" ]; then
|
||||
echo "ERROR: Failed to create release. Check BUILD_TOKEN permissions."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Upload all artifacts
|
||||
find artifacts/ -type f \( -name "*.deb" -o -name "*.AppImage" -o -name "*.msi" -o -name "*.exe" -o -name "*.dmg" \) | while read file; do
|
||||
filename=$(basename "$file")
|
||||
echo "Uploading ${filename}..."
|
||||
curl -s -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/octet-stream" \
|
||||
--data-binary "@${file}" \
|
||||
"${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}/releases/${RELEASE_ID}/assets?name=${filename}"
|
||||
done
|
||||
@@ -1,65 +0,0 @@
|
||||
name: Cleanup Old Releases
|
||||
|
||||
on:
|
||||
# Run after release and sidecar workflows complete
|
||||
schedule:
|
||||
- cron: '0 6 * * *' # Daily at 6am UTC
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
cleanup:
|
||||
name: Remove old releases
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
KEEP_COUNT: 5
|
||||
steps:
|
||||
- name: Cleanup old app releases
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
|
||||
# Get all releases, sorted newest first (API default)
|
||||
RELEASES=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases?limit=50")
|
||||
|
||||
# Separate app releases (v*) and sidecar releases (sidecar-v*)
|
||||
APP_IDS=$(echo "$RELEASES" | jq -r '[.[] | select(.tag_name | startswith("v") and (startswith("sidecar") | not)) | .id] | .[]')
|
||||
SIDECAR_IDS=$(echo "$RELEASES" | jq -r '[.[] | select(.tag_name | startswith("sidecar-v")) | .id] | .[]')
|
||||
|
||||
# Delete app releases beyond KEEP_COUNT
|
||||
COUNT=0
|
||||
for ID in $APP_IDS; do
|
||||
COUNT=$((COUNT + 1))
|
||||
if [ $COUNT -le ${{ env.KEEP_COUNT }} ]; then
|
||||
continue
|
||||
fi
|
||||
TAG=$(echo "$RELEASES" | jq -r ".[] | select(.id == $ID) | .tag_name")
|
||||
echo "Deleting app release $ID ($TAG)..."
|
||||
curl -s -o /dev/null -w "HTTP %{http_code}\n" -X DELETE \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/$ID"
|
||||
# Also delete the tag
|
||||
curl -s -o /dev/null -X DELETE \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/tags/$TAG"
|
||||
done
|
||||
|
||||
# Delete sidecar releases beyond KEEP_COUNT
|
||||
COUNT=0
|
||||
for ID in $SIDECAR_IDS; do
|
||||
COUNT=$((COUNT + 1))
|
||||
if [ $COUNT -le ${{ env.KEEP_COUNT }} ]; then
|
||||
continue
|
||||
fi
|
||||
TAG=$(echo "$RELEASES" | jq -r ".[] | select(.id == $ID) | .tag_name")
|
||||
echo "Deleting sidecar release $ID ($TAG)..."
|
||||
curl -s -o /dev/null -w "HTTP %{http_code}\n" -X DELETE \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/$ID"
|
||||
curl -s -o /dev/null -X DELETE \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/tags/$TAG"
|
||||
done
|
||||
|
||||
echo "Cleanup complete. Kept latest ${{ env.KEEP_COUNT }} of each type."
|
||||
@@ -1,305 +0,0 @@
|
||||
name: Release
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
bump-version:
|
||||
name: Bump version and tag
|
||||
# Skip if this is a version-bump commit (avoid infinite loop)
|
||||
if: "!contains(github.event.head_commit.message, '[skip ci]')"
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
new_version: ${{ steps.bump.outputs.new_version }}
|
||||
tag: ${{ steps.bump.outputs.tag }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Configure git
|
||||
run: |
|
||||
git config user.name "Gitea Actions"
|
||||
git config user.email "actions@gitea.local"
|
||||
|
||||
- name: Bump patch version
|
||||
id: bump
|
||||
run: |
|
||||
# Read current version from package.json
|
||||
CURRENT=$(grep '"version"' package.json | head -1 | sed 's/.*"version": *"\([^"]*\)".*/\1/')
|
||||
echo "Current version: ${CURRENT}"
|
||||
|
||||
# Increment patch number
|
||||
MAJOR=$(echo "${CURRENT}" | cut -d. -f1)
|
||||
MINOR=$(echo "${CURRENT}" | cut -d. -f2)
|
||||
PATCH=$(echo "${CURRENT}" | cut -d. -f3)
|
||||
NEW_PATCH=$((PATCH + 1))
|
||||
NEW_VERSION="${MAJOR}.${MINOR}.${NEW_PATCH}"
|
||||
echo "New version: ${NEW_VERSION}"
|
||||
|
||||
# Update package.json
|
||||
sed -i "s/\"version\": \"${CURRENT}\"/\"version\": \"${NEW_VERSION}\"/" package.json
|
||||
|
||||
# Update src-tauri/tauri.conf.json
|
||||
sed -i "s/\"version\": \"${CURRENT}\"/\"version\": \"${NEW_VERSION}\"/" src-tauri/tauri.conf.json
|
||||
|
||||
# Update src-tauri/Cargo.toml (match version = "x.y.z" in [package] section)
|
||||
sed -i "s/^version = \"${CURRENT}\"/version = \"${NEW_VERSION}\"/" src-tauri/Cargo.toml
|
||||
|
||||
echo "new_version=${NEW_VERSION}" >> $GITHUB_OUTPUT
|
||||
echo "tag=v${NEW_VERSION}" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Commit and tag
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
NEW_VERSION="${{ steps.bump.outputs.new_version }}"
|
||||
git add package.json src-tauri/tauri.conf.json src-tauri/Cargo.toml
|
||||
git commit -m "chore: bump version to ${NEW_VERSION} [skip ci]"
|
||||
git tag "v${NEW_VERSION}"
|
||||
|
||||
# Push using token for authentication (rebase in case another workflow pushed first)
|
||||
REMOTE_URL=$(git remote get-url origin | sed "s|://|://gitea-actions:${BUILD_TOKEN}@|")
|
||||
git pull --rebase "${REMOTE_URL}" main || true
|
||||
git push "${REMOTE_URL}" HEAD:main
|
||||
git push "${REMOTE_URL}" "v${NEW_VERSION}"
|
||||
|
||||
- name: Create Gitea release
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
TAG="${{ steps.bump.outputs.tag }}"
|
||||
RELEASE_NAME="Voice to Notes ${TAG}"
|
||||
|
||||
curl -s -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"tag_name\": \"${TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated build.\", \"draft\": false, \"prerelease\": false}" \
|
||||
"${REPO_API}/releases"
|
||||
echo "Created release: ${RELEASE_NAME}"
|
||||
|
||||
# ── Platform builds (run after version bump) ──
|
||||
|
||||
build-linux:
|
||||
name: Build App (Linux)
|
||||
needs: bump-version
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
NODE_VERSION: "20"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ needs.bump-version.outputs.tag }}
|
||||
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
|
||||
- name: Install Rust stable
|
||||
run: |
|
||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
|
||||
echo "$HOME/.cargo/bin" >> $GITHUB_PATH
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf xdg-utils rpm
|
||||
|
||||
- name: Install npm dependencies
|
||||
run: npm ci
|
||||
|
||||
- name: Build Tauri app
|
||||
run: npm run tauri build
|
||||
|
||||
- name: Upload to release
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
sudo apt-get install -y jq
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
|
||||
TAG="${{ needs.bump-version.outputs.tag }}"
|
||||
echo "Release tag: ${TAG}"
|
||||
|
||||
RELEASE_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/tags/${TAG}" | jq -r '.id // empty')
|
||||
|
||||
if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
|
||||
echo "ERROR: Failed to find release for tag ${TAG}."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Release ID: ${RELEASE_ID}"
|
||||
|
||||
find src-tauri/target/release/bundle -type f \( -name "*.deb" -o -name "*.rpm" \) | while IFS= read -r file; do
|
||||
filename=$(basename "$file")
|
||||
encoded_name=$(echo "$filename" | sed 's/ /%20/g')
|
||||
echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
|
||||
|
||||
ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
|
||||
if [ -n "${ASSET_ID}" ]; then
|
||||
curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
|
||||
fi
|
||||
|
||||
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/octet-stream" \
|
||||
-T "$file" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
|
||||
echo "Upload response: HTTP ${HTTP_CODE}"
|
||||
done
|
||||
|
||||
build-windows:
|
||||
name: Build App (Windows)
|
||||
needs: bump-version
|
||||
runs-on: windows-latest
|
||||
env:
|
||||
NODE_VERSION: "20"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ needs.bump-version.outputs.tag }}
|
||||
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
|
||||
- name: Install Rust stable
|
||||
shell: powershell
|
||||
run: |
|
||||
if (Get-Command rustup -ErrorAction SilentlyContinue) {
|
||||
rustup default stable
|
||||
} else {
|
||||
Invoke-WebRequest -Uri https://win.rustup.rs/x86_64 -OutFile rustup-init.exe
|
||||
.\rustup-init.exe -y --default-toolchain stable
|
||||
echo "$env:USERPROFILE\.cargo\bin" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
|
||||
}
|
||||
|
||||
- name: Install npm dependencies
|
||||
shell: powershell
|
||||
run: npm ci
|
||||
|
||||
- name: Build Tauri app
|
||||
shell: powershell
|
||||
run: npm run tauri build
|
||||
|
||||
- name: Upload to release
|
||||
shell: powershell
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
$REPO_API = "${{ github.server_url }}/api/v1/repos/${{ github.repository }}"
|
||||
$Headers = @{ "Authorization" = "token $env:BUILD_TOKEN" }
|
||||
|
||||
$TAG = "${{ needs.bump-version.outputs.tag }}"
|
||||
Write-Host "Release tag: ${TAG}"
|
||||
|
||||
$release = Invoke-RestMethod -Uri "${REPO_API}/releases/tags/${TAG}" -Headers $Headers -ErrorAction Stop
|
||||
$RELEASE_ID = $release.id
|
||||
Write-Host "Release ID: ${RELEASE_ID}"
|
||||
|
||||
Get-ChildItem -Path src-tauri\target\release\bundle -Recurse -Include *.msi,*-setup.exe | ForEach-Object {
|
||||
$filename = $_.Name
|
||||
$encodedName = [System.Uri]::EscapeDataString($filename)
|
||||
$size = [math]::Round($_.Length / 1MB, 1)
|
||||
Write-Host "Uploading ${filename} (${size} MB)..."
|
||||
|
||||
try {
|
||||
$assets = Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets" -Headers $Headers
|
||||
$existing = $assets | Where-Object { $_.name -eq $filename }
|
||||
if ($existing) {
|
||||
Invoke-RestMethod -Uri "${REPO_API}/releases/${RELEASE_ID}/assets/$($existing.id)" -Method Delete -Headers $Headers
|
||||
}
|
||||
} catch {}
|
||||
|
||||
# Use curl for streaming upload (Invoke-RestMethod fails on large files)
|
||||
$uploadUrl = "${REPO_API}/releases/${RELEASE_ID}/assets?name=${encodedName}"
|
||||
$result = curl.exe --fail --silent --show-error `
|
||||
-X POST `
|
||||
-H "Authorization: token $env:BUILD_TOKEN" `
|
||||
-H "Content-Type: application/octet-stream" `
|
||||
-T "$($_.FullName)" `
|
||||
"$uploadUrl" 2>&1
|
||||
if ($LASTEXITCODE -eq 0) {
|
||||
Write-Host "Upload successful: ${filename}"
|
||||
} else {
|
||||
Write-Host "WARNING: Upload failed for ${filename}: ${result}"
|
||||
}
|
||||
}
|
||||
|
||||
build-macos:
|
||||
name: Build App (macOS)
|
||||
needs: bump-version
|
||||
runs-on: macos-latest
|
||||
env:
|
||||
NODE_VERSION: "20"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ needs.bump-version.outputs.tag }}
|
||||
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
|
||||
- name: Install Rust stable
|
||||
run: |
|
||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
|
||||
echo "$HOME/.cargo/bin" >> $GITHUB_PATH
|
||||
|
||||
- name: Install system dependencies
|
||||
run: brew install --quiet create-dmg || true
|
||||
|
||||
- name: Install npm dependencies
|
||||
run: npm ci
|
||||
|
||||
- name: Build Tauri app
|
||||
run: npm run tauri build
|
||||
|
||||
- name: Upload to release
|
||||
env:
|
||||
BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
|
||||
run: |
|
||||
which jq || brew install jq
|
||||
|
||||
REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
|
||||
|
||||
TAG="${{ needs.bump-version.outputs.tag }}"
|
||||
echo "Release tag: ${TAG}"
|
||||
|
||||
RELEASE_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/tags/${TAG}" | jq -r '.id // empty')
|
||||
|
||||
if [ -z "${RELEASE_ID}" ] || [ "${RELEASE_ID}" = "null" ]; then
|
||||
echo "ERROR: Failed to find release for tag ${TAG}."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Release ID: ${RELEASE_ID}"
|
||||
|
||||
find src-tauri/target/release/bundle -type f -name "*.dmg" | while IFS= read -r file; do
|
||||
filename=$(basename "$file")
|
||||
encoded_name=$(echo "$filename" | sed 's/ /%20/g')
|
||||
echo "Uploading ${filename} ($(du -h "$file" | cut -f1))..."
|
||||
|
||||
ASSET_ID=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets" | jq -r ".[] | select(.name == \"${filename}\") | .id // empty")
|
||||
if [ -n "${ASSET_ID}" ]; then
|
||||
curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets/${ASSET_ID}"
|
||||
fi
|
||||
|
||||
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
|
||||
-H "Authorization: token ${BUILD_TOKEN}" \
|
||||
-H "Content-Type: application/octet-stream" \
|
||||
-T "$file" \
|
||||
"${REPO_API}/releases/${RELEASE_ID}/assets?name=${encoded_name}")
|
||||
echo "Upload response: HTTP ${HTTP_CODE}"
|
||||
done
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -50,6 +50,5 @@ Thumbs.db
|
||||
# Sidecar build artifacts
|
||||
src-tauri/binaries/*
|
||||
!src-tauri/binaries/.gitkeep
|
||||
src-tauri/sidecar.zip
|
||||
python/dist/
|
||||
python/build/
|
||||
|
||||
140
CONTRIBUTING.md
140
CONTRIBUTING.md
@@ -1,140 +0,0 @@
|
||||
# Contributing to Voice to Notes
|
||||
|
||||
Thank you for your interest in contributing! This guide covers how to set up the project for development and submit changes.
|
||||
|
||||
## Development Setup
|
||||
|
||||
### Prerequisites
|
||||
|
||||
- **Node.js 20+** and npm
|
||||
- **Rust** (stable toolchain)
|
||||
- **Python 3.11+** with [uv](https://docs.astral.sh/uv/) (recommended) or pip
|
||||
- **System libraries (Linux only):**
|
||||
```bash
|
||||
sudo apt install libgtk-3-dev libwebkit2gtk-4.1-dev libappindicator3-dev librsvg2-dev patchelf xdg-utils
|
||||
```
|
||||
|
||||
### Clone and Install
|
||||
|
||||
```bash
|
||||
git clone https://repo.anhonesthost.net/MacroPad/voice-to-notes.git
|
||||
cd voice-to-notes
|
||||
|
||||
# Frontend
|
||||
npm install
|
||||
|
||||
# Python sidecar
|
||||
cd python && pip install -e ".[dev]" && cd ..
|
||||
```
|
||||
|
||||
### Running in Dev Mode
|
||||
|
||||
```bash
|
||||
npm run tauri:dev
|
||||
```
|
||||
|
||||
This runs the Svelte dev server + Tauri with hot-reload. The Python sidecar runs from your system Python (no PyInstaller needed in dev mode).
|
||||
|
||||
### Building
|
||||
|
||||
```bash
|
||||
# Build the Python sidecar (frozen binary)
|
||||
cd python && python build_sidecar.py --cpu-only && cd ..
|
||||
|
||||
# Build the full app
|
||||
npm run tauri build
|
||||
```
|
||||
|
||||
## Project Structure
|
||||
|
||||
```
|
||||
src/ # Svelte 5 frontend
|
||||
lib/components/ # Reusable UI components
|
||||
lib/stores/ # Svelte stores (app state)
|
||||
routes/ # SvelteKit pages
|
||||
src-tauri/ # Rust backend (Tauri v2)
|
||||
src/sidecar/ # Python sidecar lifecycle (download, extract, IPC)
|
||||
src/commands/ # Tauri command handlers
|
||||
src/db/ # SQLite database layer
|
||||
python/ # Python ML sidecar
|
||||
voice_to_notes/ # Main package
|
||||
services/ # Transcription, diarization, AI, export
|
||||
ipc/ # JSON-line IPC protocol
|
||||
hardware/ # GPU/CPU detection
|
||||
.gitea/workflows/ # CI/CD pipelines
|
||||
docs/ # Documentation
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
||||
The app has three layers:
|
||||
|
||||
1. **Frontend (Svelte)** — UI, audio playback (wavesurfer.js), transcript editing (TipTap)
|
||||
2. **Backend (Rust/Tauri)** — Desktop integration, file access, SQLite, sidecar process management
|
||||
3. **Sidecar (Python)** — ML inference (faster-whisper, pyannote.audio), AI chat, export
|
||||
|
||||
Rust and Python communicate via **JSON-line IPC** over stdin/stdout pipes. Each request has an `id`, `type`, and `payload`. The Python sidecar runs as a child process managed by `SidecarManager` in Rust.
|
||||
|
||||
## Conventions
|
||||
|
||||
### Rust
|
||||
- Follow standard Rust conventions
|
||||
- Run `cargo fmt` and `cargo clippy` before committing
|
||||
- Tauri commands go in `src-tauri/src/commands/`
|
||||
|
||||
### Python
|
||||
- Python 3.11+, type hints everywhere
|
||||
- Use `ruff` for linting: `ruff check python/`
|
||||
- Tests with pytest: `cd python && pytest`
|
||||
- IPC messages: JSON-line format with `id`, `type`, `payload` fields
|
||||
|
||||
### TypeScript / Svelte
|
||||
- Svelte 5 runes (`$state`, `$derived`, `$effect`)
|
||||
- Strict TypeScript
|
||||
- Components in `src/lib/components/`
|
||||
- State in `src/lib/stores/`
|
||||
|
||||
### General
|
||||
- All timestamps in milliseconds (integer)
|
||||
- UUIDs as primary keys in the database
|
||||
- Don't bundle API keys or secrets — those are user-configured
|
||||
|
||||
## Submitting Changes
|
||||
|
||||
1. Fork the repository
|
||||
2. Create a feature branch: `git checkout -b my-feature`
|
||||
3. Make your changes
|
||||
4. Test locally with `npm run tauri:dev`
|
||||
5. Run linters: `cargo fmt && cargo clippy`, `ruff check python/`
|
||||
6. Commit with a clear message describing the change
|
||||
7. Open a Pull Request against `main`
|
||||
|
||||
## CI/CD
|
||||
|
||||
Pushes to `main` automatically:
|
||||
- Bump the app version and create a release (`release.yml`)
|
||||
- Build app installers for all platforms
|
||||
|
||||
Changes to `python/` also trigger sidecar builds (`build-sidecar.yml`).
|
||||
|
||||
## Areas for Contribution
|
||||
|
||||
- UI/UX improvements
|
||||
- New export formats
|
||||
- Additional AI provider integrations
|
||||
- Performance optimizations
|
||||
- Accessibility improvements
|
||||
- Documentation and translations
|
||||
- Bug reports and testing on different platforms
|
||||
|
||||
## Reporting Issues
|
||||
|
||||
Open an issue on the [repository](https://repo.anhonesthost.net/MacroPad/voice-to-notes/issues) with:
|
||||
- Steps to reproduce
|
||||
- Expected vs actual behavior
|
||||
- Platform and version info
|
||||
- Sidecar logs (`%LOCALAPPDATA%\com.voicetonotes.app\sidecar.log` on Windows)
|
||||
|
||||
## License
|
||||
|
||||
By contributing, you agree that your contributions will be licensed under the [MIT License](LICENSE).
|
||||
119
README.md
119
README.md
@@ -1,55 +1,32 @@
|
||||
# Voice to Notes
|
||||
|
||||
A desktop application that transcribes audio and video recordings with speaker identification, synchronized playback, and AI-powered analysis. Export to SRT, WebVTT, ASS captions, plain text, or Markdown.
|
||||
A desktop application that transcribes audio/video recordings with speaker identification, producing editable transcriptions with synchronized audio playback.
|
||||
|
||||
## Features
|
||||
|
||||
- **Speech-to-Text** — Accurate transcription via faster-whisper with word-level timestamps. Supports 99 languages.
|
||||
- **Speaker Identification** — Detect and label speakers using pyannote.audio. Rename speakers for clean exports.
|
||||
- **GPU Acceleration** — CUDA support for NVIDIA GPUs (Windows/Linux). Falls back to CPU automatically.
|
||||
- **Synchronized Playback** — Click any word to seek. Waveform visualization via wavesurfer.js.
|
||||
- **AI Chat** — Ask questions about your transcript. Works with Ollama (local), OpenAI, Anthropic, or any OpenAI-compatible API.
|
||||
- **Export** — SRT, WebVTT, ASS, plain text, Markdown — all with speaker labels.
|
||||
- **Cross-Platform** — Linux, Windows, macOS (Apple Silicon).
|
||||
|
||||
## Quick Start
|
||||
|
||||
1. Download the installer from [Releases](https://repo.anhonesthost.net/MacroPad/voice-to-notes/releases)
|
||||
2. On first launch, choose **CPU** or **CUDA** sidecar (the AI engine downloads separately, ~500MB–2GB)
|
||||
3. Import an audio/video file and click **Transcribe**
|
||||
|
||||
See the full [User Guide](docs/USER_GUIDE.md) for detailed setup and usage instructions.
|
||||
- **Speech-to-Text Transcription** — Accurate transcription via faster-whisper (Whisper models) with word-level timestamps
|
||||
- **Speaker Identification (Diarization)** — Detect and distinguish between speakers using pyannote.audio
|
||||
- **Synchronized Playback** — Click any word to seek to that point in the audio (Web Audio API for instant playback)
|
||||
- **AI Integration** — Ask questions about your transcript via OpenAI, Anthropic, or any OpenAI-compatible API (LiteLLM proxies, Ollama, vLLM)
|
||||
- **Export Formats** — SRT, WebVTT, ASS captions, plain text, and Markdown with speaker labels
|
||||
- **Cross-Platform** — Builds for Linux, Windows, and macOS (Apple Silicon)
|
||||
|
||||
## Platform Support
|
||||
|
||||
| Platform | Architecture | Installers |
|
||||
|----------|-------------|------------|
|
||||
| Linux | x86_64 | .deb, .rpm |
|
||||
| Windows | x86_64 | .msi, .exe (NSIS) |
|
||||
| macOS | ARM (Apple Silicon) | .dmg |
|
||||
|
||||
## Architecture
|
||||
|
||||
The app is split into two independently versioned components:
|
||||
|
||||
- **App** (v0.2.x) — Tauri desktop shell with Svelte frontend. Small installer (~50MB).
|
||||
- **Sidecar** (v1.x) — Python ML engine (faster-whisper, pyannote.audio). Downloaded on first launch. CPU (~500MB) or CUDA (~2GB) variants.
|
||||
|
||||
This separation means app UI updates don't require re-downloading the sidecar, and sidecar updates don't require reinstalling the app.
|
||||
| Platform | Architecture | Status |
|
||||
|----------|-------------|--------|
|
||||
| Linux | x86_64 | Supported |
|
||||
| Windows | x86_64 | Supported |
|
||||
| macOS | ARM (Apple Silicon) | Supported |
|
||||
|
||||
## Tech Stack
|
||||
|
||||
| Component | Technology |
|
||||
|-----------|-----------|
|
||||
| Desktop shell | Tauri v2 (Rust + Svelte 5 / TypeScript) |
|
||||
| Transcription | faster-whisper (CTranslate2) |
|
||||
| Speaker ID | pyannote.audio 3.1 |
|
||||
| Audio UI | wavesurfer.js |
|
||||
| Transcript editor | TipTap (ProseMirror) |
|
||||
| AI (local) | Ollama (any model) |
|
||||
| AI (cloud) | OpenAI, Anthropic, OpenAI-compatible |
|
||||
| Caption export | pysubs2 |
|
||||
| Database | SQLite (rusqlite) |
|
||||
- **Desktop shell:** Tauri v2 (Rust backend + Svelte 5 / TypeScript frontend)
|
||||
- **ML pipeline:** Python sidecar (faster-whisper, pyannote.audio) — frozen via PyInstaller for distribution
|
||||
- **Audio playback:** wavesurfer.js with Web Audio API backend
|
||||
- **AI providers:** OpenAI, Anthropic, OpenAI-compatible endpoints (local or remote)
|
||||
- **Local AI:** Bundled llama-server (llama.cpp)
|
||||
- **Caption export:** pysubs2
|
||||
|
||||
## Development
|
||||
|
||||
@@ -57,8 +34,8 @@ This separation means app UI updates don't require re-downloading the sidecar, a
|
||||
|
||||
- Node.js 20+
|
||||
- Rust (stable)
|
||||
- Python 3.11+ with uv or pip
|
||||
- Linux: `libgtk-3-dev`, `libwebkit2gtk-4.1-dev`, `libappindicator3-dev`, `librsvg2-dev`
|
||||
- Python 3.11+ with ML dependencies
|
||||
- System: `libgtk-3-dev`, `libwebkit2gtk-4.1-dev` (Linux)
|
||||
|
||||
### Getting Started
|
||||
|
||||
@@ -67,63 +44,49 @@ This separation means app UI updates don't require re-downloading the sidecar, a
|
||||
npm install
|
||||
|
||||
# Install Python sidecar dependencies
|
||||
cd python && pip install -e ".[dev]" && cd ..
|
||||
cd python && pip install -e . && cd ..
|
||||
|
||||
# Run in dev mode (uses system Python for the sidecar)
|
||||
npm run tauri:dev
|
||||
```
|
||||
|
||||
### Building
|
||||
### Building for Distribution
|
||||
|
||||
```bash
|
||||
# Build the frozen Python sidecar (CPU-only)
|
||||
cd python && python build_sidecar.py --cpu-only && cd ..
|
||||
# Build the frozen Python sidecar
|
||||
npm run sidecar:build
|
||||
|
||||
# Build with CUDA support
|
||||
cd python && python build_sidecar.py --with-cuda && cd ..
|
||||
|
||||
# Build the Tauri app
|
||||
# Build the Tauri app (requires sidecar in src-tauri/binaries/)
|
||||
npm run tauri build
|
||||
```
|
||||
|
||||
### CI/CD
|
||||
|
||||
Two Gitea Actions workflows in `.gitea/workflows/`:
|
||||
Gitea Actions workflows are in `.gitea/workflows/`. The build pipeline:
|
||||
|
||||
**`release.yml`** — Triggers on push to main:
|
||||
1. Bumps app version (patch), creates git tag and Gitea release
|
||||
2. Builds lightweight app installers for all platforms (no sidecar bundled)
|
||||
|
||||
**`build-sidecar.yml`** — Triggers on changes to `python/` or manual dispatch:
|
||||
1. Bumps sidecar version, creates `sidecar-v*` tag and release
|
||||
2. Builds CPU + CUDA variants for Linux/Windows, CPU for macOS
|
||||
3. Uploads as separate release assets
|
||||
1. **Build sidecar** — PyInstaller-frozen Python binary per platform (CPU-only PyTorch)
|
||||
2. **Build Tauri app** — Bundles the sidecar via `externalBin`, produces .deb/.AppImage (Linux), .msi (Windows), .dmg (macOS)
|
||||
|
||||
#### Required Secrets
|
||||
|
||||
| Secret | Purpose |
|
||||
|--------|---------|
|
||||
| `BUILD_TOKEN` | Gitea API token for creating releases and pushing tags |
|
||||
| Secret | Purpose | Required? |
|
||||
|--------|---------|-----------|
|
||||
| `TAURI_SIGNING_PRIVATE_KEY` | Signs Tauri update bundles | Optional (for auto-updates) |
|
||||
|
||||
No other secrets are needed for building. AI provider API keys and HuggingFace tokens are configured by end users in the app's Settings.
|
||||
|
||||
### Project Structure
|
||||
|
||||
```
|
||||
src/ # Svelte 5 frontend
|
||||
lib/components/ # UI components (waveform, transcript editor, settings, etc.)
|
||||
lib/stores/ # Svelte stores (settings, transcript state)
|
||||
routes/ # SvelteKit pages
|
||||
src-tauri/ # Rust backend
|
||||
src/sidecar/ # Sidecar process manager (download, extract, IPC)
|
||||
src/commands/ # Tauri command handlers
|
||||
nsis-hooks.nsh # Windows uninstall cleanup
|
||||
python/ # Python sidecar
|
||||
voice_to_notes/ # Python package (transcription, diarization, AI, export)
|
||||
build_sidecar.py # PyInstaller build script
|
||||
voice_to_notes.spec # PyInstaller spec
|
||||
.gitea/workflows/ # CI/CD (release.yml, build-sidecar.yml)
|
||||
docs/ # Documentation
|
||||
src/ # Svelte 5 frontend
|
||||
src-tauri/ # Rust backend (Tauri commands, sidecar manager, SQLite)
|
||||
python/ # Python sidecar (transcription, diarization, AI)
|
||||
voice_to_notes/ # Python package
|
||||
build_sidecar.py # PyInstaller build script
|
||||
voice_to_notes.spec # PyInstaller spec
|
||||
.gitea/workflows/ # Gitea Actions CI/CD
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
[MIT](LICENSE)
|
||||
MIT
|
||||
|
||||
@@ -1,240 +0,0 @@
|
||||
# Voice to Notes — User Guide
|
||||
|
||||
## Getting Started
|
||||
|
||||
### Installation
|
||||
|
||||
Download the installer for your platform from the [Releases](https://repo.anhonesthost.net/MacroPad/voice-to-notes/releases) page:
|
||||
|
||||
- **Windows:** `.msi` or `-setup.exe`
|
||||
- **Linux:** `.deb` or `.rpm`
|
||||
- **macOS:** `.dmg`
|
||||
|
||||
### First-Time Setup
|
||||
|
||||
On first launch, Voice to Notes will prompt you to download its AI engine (the "sidecar"):
|
||||
|
||||
1. Choose **Standard (CPU)** (~500 MB) or **GPU Accelerated (CUDA)** (~2 GB)
|
||||
- Choose CUDA if you have an NVIDIA GPU for significantly faster transcription
|
||||
- CPU works on all computers
|
||||
2. Click **Download & Install** and wait for the download to complete
|
||||
3. The app will proceed to the main interface once the sidecar is ready
|
||||
|
||||
The sidecar only needs to be downloaded once. Updates are detected automatically on launch.
|
||||
|
||||
---
|
||||
|
||||
## Basic Workflow
|
||||
|
||||
### 1. Import Audio or Video
|
||||
|
||||
- Click **Import Audio** or press **Ctrl+O** (Cmd+O on Mac)
|
||||
- **Audio formats:** MP3, WAV, FLAC, OGG, M4A, AAC, WMA
|
||||
- **Video formats:** MP4, MKV, AVI, MOV, WebM — audio is automatically extracted
|
||||
|
||||
> **Note:** Video file import requires [FFmpeg](#installing-ffmpeg) to be installed on your system.
|
||||
|
||||
### 2. Transcribe
|
||||
|
||||
After importing, click **Transcribe** to start the transcription pipeline:
|
||||
|
||||
- **Transcription:** Converts speech to text with word-level timestamps
|
||||
- **Speaker Detection:** Identifies different speakers (if configured — see [Speaker Detection](#speaker-detection))
|
||||
- A progress bar shows the current stage and percentage
|
||||
|
||||
### 3. Review and Edit
|
||||
|
||||
- The **waveform** displays at the top — click anywhere to seek
|
||||
- The **transcript** shows below with speaker labels and timestamps
|
||||
- **Click any word** in the transcript to jump to that point in the audio
|
||||
- The current word highlights during playback
|
||||
- **Edit text** directly in the transcript — word timings are preserved
|
||||
|
||||
### 4. Export
|
||||
|
||||
Click **Export** and choose a format:
|
||||
|
||||
| Format | Extension | Best For |
|
||||
|--------|-----------|----------|
|
||||
| SRT | `.srt` | Video subtitles (most compatible) |
|
||||
| WebVTT | `.vtt` | Web video players, HTML5 |
|
||||
| ASS/SSA | `.ass` | Styled subtitles with speaker colors |
|
||||
| Plain Text | `.txt` | Reading, sharing, pasting |
|
||||
| Markdown | `.md` | Documentation, notes |
|
||||
|
||||
All formats include speaker labels when speaker detection is enabled.
|
||||
|
||||
### 5. Save Project
|
||||
|
||||
- **Ctrl+S** (Cmd+S) saves the current project as a `.vtn` file
|
||||
- This preserves the full transcript, speaker assignments, and edits
|
||||
- Reopen later to continue editing or re-export
|
||||
|
||||
---
|
||||
|
||||
## Playback Controls
|
||||
|
||||
| Action | Shortcut |
|
||||
|--------|----------|
|
||||
| Play / Pause | **Space** |
|
||||
| Skip back 5s | **Left Arrow** |
|
||||
| Skip forward 5s | **Right Arrow** |
|
||||
| Seek to word | Click any word in the transcript |
|
||||
| Import audio | **Ctrl+O** / **Cmd+O** |
|
||||
| Open settings | **Ctrl+,** / **Cmd+,** |
|
||||
|
||||
---
|
||||
|
||||
## Speaker Detection
|
||||
|
||||
Speaker detection (diarization) identifies who is speaking at each point in the audio. It requires a one-time setup:
|
||||
|
||||
### Setup
|
||||
|
||||
1. Go to **Settings > Speakers**
|
||||
2. Create a free account at [huggingface.co](https://huggingface.co/join)
|
||||
3. Accept the license on **all three** model pages:
|
||||
- [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1)
|
||||
- [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0)
|
||||
- [pyannote/speaker-diarization-community-1](https://huggingface.co/pyannote/speaker-diarization-community-1)
|
||||
4. Create a token at [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) (read access is sufficient)
|
||||
5. Paste the token in Settings and click **Test & Download Model**
|
||||
|
||||
### Speaker Options
|
||||
|
||||
- **Number of speakers:** Set to auto-detect or specify a fixed number for faster results
|
||||
- **Skip speaker detection:** Check this to only transcribe without identifying speakers
|
||||
|
||||
### Managing Speakers
|
||||
|
||||
After transcription, speakers appear as "Speaker 1", "Speaker 2", etc. in the left sidebar. Double-click a speaker name to rename it — the new name appears throughout the transcript and in exports.
|
||||
|
||||
---
|
||||
|
||||
## AI Chat
|
||||
|
||||
The AI chat panel lets you ask questions about your transcript. The AI sees the full transcript with speaker labels as context.
|
||||
|
||||
Example prompts:
|
||||
- "Summarize this conversation"
|
||||
- "What were the key action items?"
|
||||
- "What did Speaker 1 say about the budget?"
|
||||
|
||||
### Setting Up Ollama (Local AI)
|
||||
|
||||
[Ollama](https://ollama.com) runs AI models locally on your computer — no API keys or internet required.
|
||||
|
||||
1. **Install Ollama:**
|
||||
- Download from [ollama.com](https://ollama.com)
|
||||
- Or on Linux: `curl -fsSL https://ollama.com/install.sh | sh`
|
||||
|
||||
2. **Pull a model:**
|
||||
```bash
|
||||
ollama pull llama3.2
|
||||
```
|
||||
Other good options: `mistral`, `gemma2`, `phi3`
|
||||
|
||||
3. **Configure in Voice to Notes:**
|
||||
- Go to **Settings > AI Provider**
|
||||
- Select **Ollama**
|
||||
- URL: `http://localhost:11434` (default, usually no change needed)
|
||||
- Model: `llama3.2` (or whichever model you pulled)
|
||||
|
||||
4. **Use:** Open the AI chat panel (right sidebar) and start asking questions
|
||||
|
||||
### Cloud AI Providers
|
||||
|
||||
If you prefer cloud-based AI:
|
||||
|
||||
**OpenAI:**
|
||||
- Select **OpenAI** in Settings > AI Provider
|
||||
- Enter your API key from [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
|
||||
- Default model: `gpt-4o-mini`
|
||||
|
||||
**Anthropic:**
|
||||
- Select **Anthropic** in Settings > AI Provider
|
||||
- Enter your API key from [console.anthropic.com](https://console.anthropic.com)
|
||||
- Default model: `claude-sonnet-4-6`
|
||||
|
||||
**OpenAI Compatible:**
|
||||
- For any provider with an OpenAI-compatible API (vLLM, LiteLLM, etc.)
|
||||
- Enter the API base URL, key, and model name
|
||||
|
||||
---
|
||||
|
||||
## Settings Reference
|
||||
|
||||
### Transcription
|
||||
|
||||
| Setting | Options | Default |
|
||||
|---------|---------|---------|
|
||||
| Whisper Model | tiny, base, small, medium, large-v3 | base |
|
||||
| Device | CPU, CUDA | CPU |
|
||||
| Language | Auto-detect, or specify (en, es, fr, etc.) | Auto-detect |
|
||||
|
||||
**Model recommendations:**
|
||||
- **tiny/base:** Fast, good for clear audio with one speaker
|
||||
- **small:** Best balance of speed and accuracy
|
||||
- **medium:** Better accuracy, noticeably slower
|
||||
- **large-v3:** Best accuracy, requires 8GB+ VRAM (GPU) or 16GB+ RAM (CPU)
|
||||
|
||||
### Debug
|
||||
|
||||
- **Enable Developer Tools:** Opens the browser inspector for debugging
|
||||
|
||||
---
|
||||
|
||||
## Installing FFmpeg
|
||||
|
||||
FFmpeg is required for importing video files (MP4, MKV, AVI, etc.). It's used to extract the audio track before transcription.
|
||||
|
||||
**Windows:**
|
||||
```
|
||||
winget install ffmpeg
|
||||
```
|
||||
Or download from [ffmpeg.org/download.html](https://ffmpeg.org/download.html) and add to your PATH.
|
||||
|
||||
**macOS:**
|
||||
```
|
||||
brew install ffmpeg
|
||||
```
|
||||
|
||||
**Linux (Debian/Ubuntu):**
|
||||
```
|
||||
sudo apt install ffmpeg
|
||||
```
|
||||
|
||||
**Linux (Fedora/RHEL):**
|
||||
```
|
||||
sudo dnf install ffmpeg
|
||||
```
|
||||
|
||||
After installing, restart Voice to Notes. FFmpeg is not needed for audio-only files (MP3, WAV, FLAC, etc.).
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Video import fails / "FFmpeg not found"
|
||||
- Install FFmpeg using the instructions above
|
||||
- Make sure `ffmpeg` is in your system PATH
|
||||
- Restart Voice to Notes after installing
|
||||
|
||||
### Transcription is slow
|
||||
- Use a smaller model (tiny or base)
|
||||
- If you have an NVIDIA GPU, select CUDA in Settings > Transcription > Device
|
||||
- Ensure you downloaded the CUDA sidecar during setup
|
||||
|
||||
### Speaker detection not working
|
||||
- Verify your HuggingFace token in Settings > Speakers
|
||||
- Click "Test & Download Model" to re-download
|
||||
- Make sure you accepted the license on all three model pages
|
||||
|
||||
### Audio won't play / No waveform
|
||||
- Check that the audio file still exists at its original location
|
||||
- Try re-importing the file
|
||||
- Supported formats: MP3, WAV, FLAC, OGG, M4A, AAC, WMA
|
||||
|
||||
### App shows "Setting up Voice to Notes"
|
||||
- This is the first-launch sidecar download — it only happens once
|
||||
- If it fails, check your internet connection and click Retry
|
||||
4
package-lock.json
generated
4
package-lock.json
generated
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "voice-to-notes",
|
||||
"version": "0.2.10",
|
||||
"version": "0.1.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "voice-to-notes",
|
||||
"version": "0.2.10",
|
||||
"version": "0.1.0",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@tauri-apps/api": "^2",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "voice-to-notes",
|
||||
"version": "0.2.46",
|
||||
"version": "0.1.0",
|
||||
"description": "Desktop app for transcribing audio/video with speaker identification",
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
|
||||
@@ -92,42 +92,34 @@ def create_venv_and_install(cpu_only: bool) -> Path:
|
||||
|
||||
# Determine python path inside venv
|
||||
if sys.platform == "win32":
|
||||
python = str(venv_dir / "Scripts" / "python.exe")
|
||||
python = str(venv_dir / "Scripts" / "python")
|
||||
else:
|
||||
python = str(venv_dir / "bin" / "python")
|
||||
|
||||
def pip_install(*args: str) -> None:
|
||||
"""Install packages. Pass package names and flags only, not 'install'."""
|
||||
def pkg_install(*args: str) -> None:
|
||||
if use_uv:
|
||||
# Use --python with the venv directory (not the python binary) for uv
|
||||
subprocess.run(
|
||||
["uv", "pip", "install", "--python", str(venv_dir), *args],
|
||||
check=True,
|
||||
)
|
||||
subprocess.run(["uv", "pip", "install", "--python", python, *args], check=True)
|
||||
else:
|
||||
subprocess.run([python, "-m", "pip", "install", *args], check=True)
|
||||
subprocess.run([python, "-m", "pip", *args], check=True)
|
||||
|
||||
if not use_uv:
|
||||
# Upgrade pip (uv doesn't need this)
|
||||
pip_install("--upgrade", "pip", "setuptools", "wheel")
|
||||
pkg_install("install", "--upgrade", "pip", "setuptools", "wheel")
|
||||
|
||||
# Install torch (CPU-only to avoid bundling ~2GB of CUDA libs)
|
||||
if cpu_only:
|
||||
print("[build] Installing PyTorch (CPU-only)")
|
||||
pip_install(
|
||||
"torch", "torchaudio",
|
||||
pkg_install(
|
||||
"install", "torch", "torchaudio",
|
||||
"--index-url", "https://download.pytorch.org/whl/cpu",
|
||||
)
|
||||
else:
|
||||
print("[build] Installing PyTorch (CUDA 12.6)")
|
||||
pip_install(
|
||||
"torch", "torchaudio",
|
||||
"--index-url", "https://download.pytorch.org/whl/cu126",
|
||||
)
|
||||
print("[build] Installing PyTorch (default, may include CUDA)")
|
||||
pkg_install("install", "torch", "torchaudio")
|
||||
|
||||
# Install project and dev deps (includes pyinstaller)
|
||||
print("[build] Installing project dependencies")
|
||||
pip_install("-e", f"{SCRIPT_DIR}[dev]")
|
||||
pkg_install("install", "-e", f"{SCRIPT_DIR}[dev]")
|
||||
|
||||
return Path(python)
|
||||
|
||||
@@ -239,9 +231,10 @@ def main() -> None:
|
||||
python = create_venv_and_install(cpu_only)
|
||||
output_dir = run_pyinstaller(python)
|
||||
download_ffmpeg(output_dir)
|
||||
rename_binary(output_dir, target_triple)
|
||||
|
||||
print(f"\n[build] Done! Sidecar built at: {output_dir}")
|
||||
print(f"[build] Copy directory to src-tauri/sidecar/ for Tauri resource bundling")
|
||||
print(f"[build] Copy contents to src-tauri/binaries/ for Tauri bundling")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "voice-to-notes"
|
||||
version = "1.0.13"
|
||||
version = "0.1.0"
|
||||
description = "Python sidecar for Voice to Notes — transcription, diarization, and AI services"
|
||||
requires-python = ">=3.11"
|
||||
license = "MIT"
|
||||
@@ -15,7 +15,6 @@ dependencies = [
|
||||
"pysubs2>=1.7.0",
|
||||
"openai>=1.0.0",
|
||||
"anthropic>=0.20.0",
|
||||
"soundfile>=0.12.0",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
|
||||
@@ -12,17 +12,15 @@ faster_whisper_datas, faster_whisper_binaries, faster_whisper_hiddenimports = co
|
||||
"faster_whisper"
|
||||
)
|
||||
pyannote_datas, pyannote_binaries, pyannote_hiddenimports = collect_all("pyannote")
|
||||
soundfile_datas, soundfile_binaries, soundfile_hiddenimports = collect_all("soundfile")
|
||||
|
||||
a = Analysis(
|
||||
["voice_to_notes/main.py"],
|
||||
pathex=[],
|
||||
binaries=ctranslate2_binaries + faster_whisper_binaries + pyannote_binaries + soundfile_binaries,
|
||||
datas=ctranslate2_datas + faster_whisper_datas + pyannote_datas + soundfile_datas,
|
||||
binaries=ctranslate2_binaries + faster_whisper_binaries + pyannote_binaries,
|
||||
datas=ctranslate2_datas + faster_whisper_datas + pyannote_datas,
|
||||
hiddenimports=[
|
||||
"torch",
|
||||
"torchaudio",
|
||||
"soundfile",
|
||||
"huggingface_hub",
|
||||
"pysubs2",
|
||||
"openai",
|
||||
@@ -31,22 +29,11 @@ a = Analysis(
|
||||
]
|
||||
+ ctranslate2_hiddenimports
|
||||
+ faster_whisper_hiddenimports
|
||||
+ pyannote_hiddenimports
|
||||
+ soundfile_hiddenimports,
|
||||
+ pyannote_hiddenimports,
|
||||
hookspath=[],
|
||||
hooksconfig={},
|
||||
runtime_hooks=[],
|
||||
excludes=[
|
||||
"tkinter", "test", "pip", "setuptools",
|
||||
# ctranslate2.converters imports torch at module level and causes
|
||||
# circular import crashes under PyInstaller. These modules are only
|
||||
# needed for model format conversion, never for inference.
|
||||
"ctranslate2.converters",
|
||||
# torchcodec is partially bundled by PyInstaller but non-functional
|
||||
# (missing FFmpeg shared libs). Excluding it forces pyannote.audio
|
||||
# to fall back to torchaudio for audio decoding.
|
||||
"torchcodec",
|
||||
],
|
||||
excludes=["tkinter", "test", "unittest", "pip", "setuptools"],
|
||||
win_no_prefer_redirects=False,
|
||||
win_private_assemblies=False,
|
||||
cipher=block_cipher,
|
||||
|
||||
@@ -105,23 +105,14 @@ def detect_hardware() -> HardwareInfo:
|
||||
# RAM info (cross-platform)
|
||||
info.ram_mb = _detect_ram_mb()
|
||||
|
||||
# CUDA detection — verify runtime libraries actually work, not just torch detection
|
||||
# CUDA detection
|
||||
try:
|
||||
import torch
|
||||
|
||||
if torch.cuda.is_available():
|
||||
# Test that CUDA runtime libraries are actually loadable
|
||||
try:
|
||||
torch.zeros(1, device="cuda")
|
||||
info.has_cuda = True
|
||||
info.cuda_device_name = torch.cuda.get_device_name(0)
|
||||
info.vram_mb = torch.cuda.get_device_properties(0).total_mem // (1024 * 1024)
|
||||
except Exception as e:
|
||||
print(
|
||||
f"[sidecar] CUDA detected but runtime unavailable: {e}. Using CPU.",
|
||||
file=sys.stderr,
|
||||
flush=True,
|
||||
)
|
||||
info.has_cuda = True
|
||||
info.cuda_device_name = torch.cuda.get_device_name(0)
|
||||
info.vram_mb = torch.cuda.get_device_properties(0).total_mem // (1024 * 1024)
|
||||
except ImportError:
|
||||
print("[sidecar] torch not available, GPU detection skipped", file=sys.stderr, flush=True)
|
||||
|
||||
|
||||
@@ -41,15 +41,11 @@ def ping_handler(msg: IPCMessage) -> IPCMessage:
|
||||
|
||||
def make_transcribe_handler() -> HandlerFunc:
|
||||
"""Create a transcription handler with a persistent TranscribeService."""
|
||||
service = None
|
||||
from voice_to_notes.services.transcribe import TranscribeService, result_to_payload
|
||||
|
||||
service = TranscribeService()
|
||||
|
||||
def handler(msg: IPCMessage) -> IPCMessage:
|
||||
nonlocal service
|
||||
if service is None:
|
||||
from voice_to_notes.services.transcribe import TranscribeService
|
||||
service = TranscribeService()
|
||||
from voice_to_notes.services.transcribe import result_to_payload
|
||||
|
||||
payload = msg.payload
|
||||
result = service.transcribe(
|
||||
request_id=msg.id,
|
||||
@@ -70,15 +66,11 @@ def make_transcribe_handler() -> HandlerFunc:
|
||||
|
||||
def make_diarize_handler() -> HandlerFunc:
|
||||
"""Create a diarization handler with a persistent DiarizeService."""
|
||||
service = None
|
||||
from voice_to_notes.services.diarize import DiarizeService, diarization_to_payload
|
||||
|
||||
service = DiarizeService()
|
||||
|
||||
def handler(msg: IPCMessage) -> IPCMessage:
|
||||
nonlocal service
|
||||
if service is None:
|
||||
from voice_to_notes.services.diarize import DiarizeService
|
||||
service = DiarizeService()
|
||||
from voice_to_notes.services.diarize import diarization_to_payload
|
||||
|
||||
payload = msg.payload
|
||||
result = service.diarize(
|
||||
request_id=msg.id,
|
||||
@@ -171,15 +163,11 @@ def make_diarize_download_handler() -> HandlerFunc:
|
||||
|
||||
def make_pipeline_handler() -> HandlerFunc:
|
||||
"""Create a full pipeline handler (transcribe + diarize + merge)."""
|
||||
service = None
|
||||
from voice_to_notes.services.pipeline import PipelineService, pipeline_result_to_payload
|
||||
|
||||
service = PipelineService()
|
||||
|
||||
def handler(msg: IPCMessage) -> IPCMessage:
|
||||
nonlocal service
|
||||
if service is None:
|
||||
from voice_to_notes.services.pipeline import PipelineService
|
||||
service = PipelineService()
|
||||
from voice_to_notes.services.pipeline import pipeline_result_to_payload
|
||||
|
||||
payload = msg.payload
|
||||
result = service.run(
|
||||
request_id=msg.id,
|
||||
@@ -205,15 +193,11 @@ def make_pipeline_handler() -> HandlerFunc:
|
||||
|
||||
def make_export_handler() -> HandlerFunc:
|
||||
"""Create an export handler."""
|
||||
service = None
|
||||
from voice_to_notes.services.export import ExportService, make_export_request
|
||||
|
||||
service = ExportService()
|
||||
|
||||
def handler(msg: IPCMessage) -> IPCMessage:
|
||||
nonlocal service
|
||||
if service is None:
|
||||
from voice_to_notes.services.export import ExportService
|
||||
service = ExportService()
|
||||
from voice_to_notes.services.export import make_export_request
|
||||
|
||||
request = make_export_request(msg.payload)
|
||||
output_path = service.export(request)
|
||||
return IPCMessage(
|
||||
@@ -227,14 +211,11 @@ def make_export_handler() -> HandlerFunc:
|
||||
|
||||
def make_ai_chat_handler() -> HandlerFunc:
|
||||
"""Create an AI chat handler with persistent AIProviderService."""
|
||||
service = None
|
||||
from voice_to_notes.services.ai_provider import create_default_service
|
||||
|
||||
service = create_default_service()
|
||||
|
||||
def handler(msg: IPCMessage) -> IPCMessage:
|
||||
nonlocal service
|
||||
if service is None:
|
||||
from voice_to_notes.services.ai_provider import create_default_service
|
||||
service = create_default_service()
|
||||
|
||||
payload = msg.payload
|
||||
action = payload.get("action", "chat")
|
||||
|
||||
@@ -254,15 +235,15 @@ def make_ai_chat_handler() -> HandlerFunc:
|
||||
)
|
||||
|
||||
if action == "configure":
|
||||
# Re-create a provider with custom settings and set it active
|
||||
# Re-create a provider with custom settings
|
||||
provider_name = payload.get("provider", "")
|
||||
config = payload.get("config", {})
|
||||
if provider_name == "local":
|
||||
from voice_to_notes.providers.local_provider import LocalProvider
|
||||
|
||||
service.register_provider("local", LocalProvider(
|
||||
base_url=config.get("base_url", "http://localhost:11434/v1"),
|
||||
model=config.get("model", "llama3.2"),
|
||||
base_url=config.get("base_url", "http://localhost:8080"),
|
||||
model=config.get("model", "local"),
|
||||
))
|
||||
elif provider_name == "openai":
|
||||
from voice_to_notes.providers.openai_provider import OpenAIProvider
|
||||
@@ -286,10 +267,6 @@ def make_ai_chat_handler() -> HandlerFunc:
|
||||
api_key=config.get("api_key"),
|
||||
api_base=config.get("api_base"),
|
||||
))
|
||||
# Set the configured provider as active
|
||||
print(f"[sidecar] Configured AI provider: {provider_name} with config: {config}", file=sys.stderr, flush=True)
|
||||
if provider_name in ("local", "openai", "anthropic", "litellm"):
|
||||
service.set_active(provider_name)
|
||||
return IPCMessage(
|
||||
id=msg.id,
|
||||
type="ai.configured",
|
||||
|
||||
@@ -5,7 +5,6 @@ from __future__ import annotations
|
||||
import signal
|
||||
import sys
|
||||
|
||||
|
||||
# CRITICAL: Capture real stdout for IPC *before* importing any ML libraries
|
||||
# that might print to stdout and corrupt the JSON-line protocol.
|
||||
from voice_to_notes.ipc.protocol import init_ipc
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
"""Local AI provider — Ollama or any OpenAI-compatible API."""
|
||||
"""Local AI provider — bundled llama-server (OpenAI-compatible API)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -9,9 +9,9 @@ from voice_to_notes.providers.base import AIProvider
|
||||
|
||||
|
||||
class LocalProvider(AIProvider):
|
||||
"""Connects to Ollama or any OpenAI-compatible API server."""
|
||||
"""Connects to bundled llama-server via its OpenAI-compatible API."""
|
||||
|
||||
def __init__(self, base_url: str = "http://localhost:11434/v1", model: str = "llama3.2") -> None:
|
||||
def __init__(self, base_url: str = "http://localhost:8080", model: str = "local") -> None:
|
||||
self._base_url = base_url.rstrip("/")
|
||||
self._model = model
|
||||
self._client: Any = None
|
||||
@@ -24,8 +24,8 @@ class LocalProvider(AIProvider):
|
||||
from openai import OpenAI
|
||||
|
||||
self._client = OpenAI(
|
||||
base_url=self._base_url,
|
||||
api_key="ollama", # Ollama doesn't require a real key
|
||||
base_url=f"{self._base_url}/v1",
|
||||
api_key="not-needed", # llama-server doesn't require an API key
|
||||
)
|
||||
except ImportError:
|
||||
raise RuntimeError(
|
||||
@@ -47,9 +47,7 @@ class LocalProvider(AIProvider):
|
||||
try:
|
||||
import urllib.request
|
||||
|
||||
# Check base URL without /v1 suffix for Ollama root endpoint
|
||||
root_url = self._base_url.replace("/v1", "")
|
||||
req = urllib.request.Request(root_url, method="GET")
|
||||
req = urllib.request.Request(f"{self._base_url}/health", method="GET")
|
||||
with urllib.request.urlopen(req, timeout=2) as resp:
|
||||
return resp.status == 200
|
||||
except Exception:
|
||||
@@ -57,4 +55,4 @@ class LocalProvider(AIProvider):
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
return "Ollama"
|
||||
return "Local (llama-server)"
|
||||
|
||||
@@ -20,81 +20,6 @@ from voice_to_notes.utils.ffmpeg import get_ffmpeg_path
|
||||
from voice_to_notes.ipc.messages import progress_message
|
||||
from voice_to_notes.ipc.protocol import write_message
|
||||
|
||||
_patched = False
|
||||
|
||||
|
||||
def _patch_pyannote_audio() -> None:
|
||||
"""Monkey-patch pyannote.audio.core.io.Audio to use torchaudio.
|
||||
|
||||
pyannote.audio has a bug where AudioDecoder (from torchcodec) is used
|
||||
unconditionally even when torchcodec is not installed, causing NameError.
|
||||
This replaces the Audio.__call__ method with a torchaudio-based version.
|
||||
"""
|
||||
global _patched
|
||||
if _patched:
|
||||
return
|
||||
_patched = True
|
||||
|
||||
try:
|
||||
import numpy as np
|
||||
import soundfile as sf
|
||||
import torch
|
||||
from pyannote.audio.core.io import Audio
|
||||
|
||||
# Cache loaded audio to avoid re-reading the entire file for every crop call.
|
||||
# For a 3-hour file, crop is called 1000+ times — without caching, each call
|
||||
# reads ~345MB from disk.
|
||||
_audio_cache: dict[str, tuple] = {}
|
||||
|
||||
def _sf_load(audio_path: str) -> tuple:
|
||||
"""Load audio via soundfile with caching."""
|
||||
key = str(audio_path)
|
||||
if key in _audio_cache:
|
||||
return _audio_cache[key]
|
||||
data, sample_rate = sf.read(key, dtype="float32")
|
||||
waveform = torch.from_numpy(np.array(data))
|
||||
if waveform.ndim == 1:
|
||||
waveform = waveform.unsqueeze(0)
|
||||
else:
|
||||
waveform = waveform.T
|
||||
_audio_cache[key] = (waveform, sample_rate)
|
||||
return waveform, sample_rate
|
||||
|
||||
def _soundfile_call(self, file: dict) -> tuple:
|
||||
"""Replacement for Audio.__call__."""
|
||||
return _sf_load(file["audio"])
|
||||
|
||||
def _soundfile_crop(self, file: dict, segment, **kwargs) -> tuple:
|
||||
"""Replacement for Audio.crop — load file once (cached) then slice.
|
||||
|
||||
Pads short segments with zeros to match the expected duration,
|
||||
which pyannote requires for batched embedding extraction.
|
||||
"""
|
||||
duration = kwargs.get("duration", None)
|
||||
waveform, sample_rate = _sf_load(file["audio"])
|
||||
# Convert segment (seconds) to sample indices
|
||||
start_sample = int(segment.start * sample_rate)
|
||||
end_sample = int(segment.end * sample_rate)
|
||||
# Clamp to bounds
|
||||
start_sample = max(0, start_sample)
|
||||
end_sample = min(waveform.shape[-1], end_sample)
|
||||
cropped = waveform[:, start_sample:end_sample]
|
||||
# Pad to expected duration if needed (pyannote batches require uniform size)
|
||||
if duration is not None:
|
||||
expected_samples = int(duration * sample_rate)
|
||||
else:
|
||||
expected_samples = int((segment.end - segment.start) * sample_rate)
|
||||
if cropped.shape[-1] < expected_samples:
|
||||
pad = torch.zeros(cropped.shape[0], expected_samples - cropped.shape[-1])
|
||||
cropped = torch.cat([cropped, pad], dim=-1)
|
||||
return cropped, sample_rate
|
||||
|
||||
Audio.__call__ = _soundfile_call # type: ignore[assignment]
|
||||
Audio.crop = _soundfile_crop # type: ignore[assignment]
|
||||
print("[sidecar] Patched pyannote Audio to use soundfile", file=sys.stderr, flush=True)
|
||||
except Exception as e:
|
||||
print(f"[sidecar] Warning: Could not patch pyannote Audio: {e}", file=sys.stderr, flush=True)
|
||||
|
||||
|
||||
def _ensure_wav(file_path: str) -> tuple[str, str | None]:
|
||||
"""Convert audio to 16kHz mono WAV if needed.
|
||||
@@ -188,7 +113,6 @@ class DiarizeService:
|
||||
]
|
||||
|
||||
last_error: Exception | None = None
|
||||
_patch_pyannote_audio()
|
||||
for model_name in models:
|
||||
try:
|
||||
from pyannote.audio import Pipeline
|
||||
@@ -288,20 +212,13 @@ class DiarizeService:
|
||||
thread.start()
|
||||
|
||||
elapsed = 0.0
|
||||
estimated_total = max(audio_duration_sec * 0.8, 30.0) if audio_duration_sec else 120.0
|
||||
duration_str = ""
|
||||
if audio_duration_sec and audio_duration_sec > 600:
|
||||
mins = int(audio_duration_sec / 60)
|
||||
duration_str = f" ({mins}min audio, this may take a while)"
|
||||
while not done_event.wait(timeout=5.0):
|
||||
elapsed += 5.0
|
||||
estimated_total = max(audio_duration_sec * 0.5, 30.0) if audio_duration_sec else 120.0
|
||||
while not done_event.wait(timeout=2.0):
|
||||
elapsed += 2.0
|
||||
pct = min(20 + int((elapsed / estimated_total) * 65), 85)
|
||||
elapsed_min = int(elapsed / 60)
|
||||
elapsed_sec = int(elapsed % 60)
|
||||
time_str = f"{elapsed_min}m{elapsed_sec:02d}s" if elapsed_min > 0 else f"{int(elapsed)}s"
|
||||
write_message(progress_message(
|
||||
request_id, pct, "diarizing",
|
||||
f"Analyzing speakers ({time_str} elapsed){duration_str}"))
|
||||
f"Analyzing speakers ({int(elapsed)}s elapsed)..."))
|
||||
|
||||
thread.join()
|
||||
|
||||
|
||||
@@ -77,28 +77,11 @@ class TranscribeService:
|
||||
file=sys.stderr,
|
||||
flush=True,
|
||||
)
|
||||
try:
|
||||
self._model = WhisperModel(
|
||||
model_name,
|
||||
device=device,
|
||||
compute_type=compute_type,
|
||||
)
|
||||
except Exception as e:
|
||||
if device != "cpu":
|
||||
print(
|
||||
f"[sidecar] Failed to load on {device}: {e}. Falling back to CPU.",
|
||||
file=sys.stderr,
|
||||
flush=True,
|
||||
)
|
||||
device = "cpu"
|
||||
compute_type = "int8"
|
||||
self._model = WhisperModel(
|
||||
model_name,
|
||||
device=device,
|
||||
compute_type=compute_type,
|
||||
)
|
||||
else:
|
||||
raise
|
||||
self._model = WhisperModel(
|
||||
model_name,
|
||||
device=device,
|
||||
compute_type=compute_type,
|
||||
)
|
||||
self._current_model_name = model_name
|
||||
self._current_device = device
|
||||
self._current_compute_type = compute_type
|
||||
@@ -113,22 +96,17 @@ class TranscribeService:
|
||||
compute_type: str = "int8",
|
||||
language: str | None = None,
|
||||
on_segment: Callable[[SegmentResult, int], None] | None = None,
|
||||
chunk_label: str | None = None,
|
||||
) -> TranscriptionResult:
|
||||
"""Transcribe an audio file with word-level timestamps.
|
||||
|
||||
Sends progress messages via IPC during processing.
|
||||
If chunk_label is set (e.g. "chunk 3/12"), messages are prefixed with it.
|
||||
"""
|
||||
prefix = f"{chunk_label}: " if chunk_label else ""
|
||||
|
||||
# Stage: loading model (skip for chunks after the first — model already loaded)
|
||||
if not chunk_label:
|
||||
write_message(progress_message(request_id, 0, "loading_model", f"Loading {model_name}..."))
|
||||
# Stage: loading model
|
||||
write_message(progress_message(request_id, 0, "loading_model", f"Loading {model_name}..."))
|
||||
model = self._ensure_model(model_name, device, compute_type)
|
||||
|
||||
# Stage: transcribing
|
||||
write_message(progress_message(request_id, 10, "transcribing", f"{prefix}Starting transcription..."))
|
||||
write_message(progress_message(request_id, 10, "transcribing", "Starting transcription..."))
|
||||
|
||||
start_time = time.time()
|
||||
segments_iter, info = model.transcribe(
|
||||
@@ -181,7 +159,7 @@ class TranscribeService:
|
||||
request_id,
|
||||
progress_pct,
|
||||
"transcribing",
|
||||
f"{prefix}Transcribing segment {segment_count} ({progress_pct}% of audio)...",
|
||||
f"Transcribing segment {segment_count} ({progress_pct}% of audio)...",
|
||||
)
|
||||
)
|
||||
|
||||
@@ -276,7 +254,6 @@ class TranscribeService:
|
||||
chunk_result = self.transcribe(
|
||||
request_id, tmp.name, model_name, device,
|
||||
compute_type, language, on_segment=chunk_on_segment,
|
||||
chunk_label=f"Chunk {chunk_idx + 1}/{num_chunks}",
|
||||
)
|
||||
|
||||
# Offset timestamps and merge
|
||||
|
||||
52
src-tauri/Cargo.lock
generated
52
src-tauri/Cargo.lock
generated
@@ -59,15 +59,6 @@ version = "1.0.102"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
|
||||
|
||||
[[package]]
|
||||
name = "arbitrary"
|
||||
version = "1.4.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c3d036a3c4ab069c7b410a2ce876bd74808d2d0888a82667669f8e783a898bf1"
|
||||
dependencies = [
|
||||
"derive_arbitrary",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "async-broadcast"
|
||||
version = "0.7.2"
|
||||
@@ -664,17 +655,6 @@ dependencies = [
|
||||
"serde_core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "derive_arbitrary"
|
||||
version = "1.4.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1e567bd82dcff979e4b03460c307b3cdc9e96fde3d73bed1496d2bc75d9dd62a"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "derive_more"
|
||||
version = "0.99.20"
|
||||
@@ -4382,7 +4362,7 @@ checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
|
||||
|
||||
[[package]]
|
||||
name = "voice-to-notes"
|
||||
version = "0.2.2"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"rusqlite",
|
||||
@@ -4394,7 +4374,6 @@ dependencies = [
|
||||
"tauri-plugin-opener",
|
||||
"thiserror 1.0.69",
|
||||
"uuid",
|
||||
"zip",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -5433,41 +5412,12 @@ dependencies = [
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zip"
|
||||
version = "2.4.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "fabe6324e908f85a1c52063ce7aa26b68dcb7eb6dbc83a2d148403c9bc3eba50"
|
||||
dependencies = [
|
||||
"arbitrary",
|
||||
"crc32fast",
|
||||
"crossbeam-utils",
|
||||
"displaydoc",
|
||||
"flate2",
|
||||
"indexmap 2.13.0",
|
||||
"memchr",
|
||||
"thiserror 2.0.18",
|
||||
"zopfli",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zmij"
|
||||
version = "1.0.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"
|
||||
|
||||
[[package]]
|
||||
name = "zopfli"
|
||||
version = "0.8.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f05cd8797d63865425ff89b5c4a48804f35ba0ce8d125800027ad6017d2b5249"
|
||||
dependencies = [
|
||||
"bumpalo",
|
||||
"crc32fast",
|
||||
"log",
|
||||
"simd-adler32",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zvariant"
|
||||
version = "5.10.0"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "voice-to-notes"
|
||||
version = "0.2.46"
|
||||
version = "0.1.0"
|
||||
description = "Voice to Notes — desktop transcription with speaker identification"
|
||||
authors = ["Voice to Notes Contributors"]
|
||||
license = "MIT"
|
||||
@@ -14,16 +14,12 @@ crate-type = ["staticlib", "cdylib", "rlib"]
|
||||
tauri-build = { version = "2", features = [] }
|
||||
|
||||
[dependencies]
|
||||
tauri = { version = "2", features = ["protocol-asset", "devtools"] }
|
||||
tauri = { version = "2", features = ["protocol-asset"] }
|
||||
tauri-plugin-opener = "2"
|
||||
serde = { version = "1", features = ["derive"] }
|
||||
serde_json = "1"
|
||||
rusqlite = { version = "0.31", features = ["bundled"] }
|
||||
uuid = { version = "1", features = ["v4", "serde"] }
|
||||
zip = { version = "2", default-features = false, features = ["deflate"] }
|
||||
thiserror = "1"
|
||||
chrono = { version = "0.4", features = ["serde"] }
|
||||
tauri-plugin-dialog = "2.6.0"
|
||||
reqwest = { version = "0.12", features = ["stream", "json"] }
|
||||
futures-util = "0.3"
|
||||
bytes = "1"
|
||||
|
||||
@@ -1,21 +1,3 @@
|
||||
fn main() {
|
||||
// Ensure sidecar.zip exists so tauri-build doesn't fail.
|
||||
// CI replaces this placeholder with the real PyInstaller sidecar archive.
|
||||
let zip_path = std::path::Path::new("sidecar.zip");
|
||||
if !zip_path.exists() {
|
||||
// Minimal valid zip (empty archive): end-of-central-directory record
|
||||
let empty_zip: [u8; 22] = [
|
||||
0x50, 0x4b, 0x05, 0x06, // EOCD signature
|
||||
0x00, 0x00, // disk number
|
||||
0x00, 0x00, // disk with central dir
|
||||
0x00, 0x00, // entries on this disk
|
||||
0x00, 0x00, // total entries
|
||||
0x00, 0x00, 0x00, 0x00, // central dir size
|
||||
0x00, 0x00, 0x00, 0x00, // central dir offset
|
||||
0x00, 0x00, // comment length
|
||||
];
|
||||
std::fs::write(zip_path, empty_zip).expect("Failed to create placeholder sidecar.zip");
|
||||
}
|
||||
|
||||
tauri_build::build()
|
||||
}
|
||||
|
||||
@@ -1,11 +0,0 @@
|
||||
; NSIS uninstall hook for Voice to Notes
|
||||
; Removes the sidecar data directory (extracted sidecar binaries + logs)
|
||||
; but preserves user data in $PROFILE\.voicetonotes (database, settings, models)
|
||||
|
||||
!macro NSIS_HOOK_POSTUNINSTALL
|
||||
; Remove the Tauri app_local_data_dir which contains:
|
||||
; - Extracted sidecar directories (voice-to-notes-sidecar/)
|
||||
; - sidecar.log
|
||||
; Path: %LOCALAPPDATA%\com.voicetonotes.app
|
||||
RMDir /r "$LOCALAPPDATA\com.voicetonotes.app"
|
||||
!macroend
|
||||
@@ -1,152 +0,0 @@
|
||||
use std::path::PathBuf;
|
||||
use std::process::Command;
|
||||
|
||||
#[cfg(target_os = "windows")]
|
||||
use std::os::windows::process::CommandExt;
|
||||
|
||||
/// Extract audio from a video file to a WAV file using ffmpeg.
|
||||
/// Returns the path to the extracted audio file.
|
||||
#[tauri::command]
|
||||
pub fn extract_audio(file_path: String, output_path: Option<String>) -> Result<String, String> {
|
||||
let input = PathBuf::from(&file_path);
|
||||
if !input.exists() {
|
||||
return Err(format!("File not found: {}", file_path));
|
||||
}
|
||||
|
||||
// Use provided output path, or fall back to a temp WAV file
|
||||
let stem = input.file_stem().unwrap_or_default().to_string_lossy();
|
||||
let output = match output_path {
|
||||
Some(ref p) => PathBuf::from(p),
|
||||
None => std::env::temp_dir().join(format!("{stem}_audio.wav")),
|
||||
};
|
||||
|
||||
eprintln!(
|
||||
"[media] Extracting audio: {} -> {}",
|
||||
input.display(),
|
||||
output.display()
|
||||
);
|
||||
|
||||
// Find ffmpeg — check sidecar extract dir first, then system PATH
|
||||
let ffmpeg = find_ffmpeg().ok_or("ffmpeg not found. Install ffmpeg or ensure it's in PATH.")?;
|
||||
|
||||
let mut cmd = Command::new(&ffmpeg);
|
||||
cmd.args([
|
||||
"-y", // Overwrite output
|
||||
"-i",
|
||||
&file_path,
|
||||
"-vn", // No video
|
||||
"-acodec",
|
||||
"pcm_s16le", // WAV PCM 16-bit
|
||||
"-ar",
|
||||
"22050", // 22kHz mono for better playback quality
|
||||
"-ac",
|
||||
"1", // Mono
|
||||
])
|
||||
.arg(output.to_str().unwrap())
|
||||
.stdout(std::process::Stdio::null())
|
||||
.stderr(std::process::Stdio::piped());
|
||||
|
||||
// Hide the console window on Windows (CREATE_NO_WINDOW = 0x08000000)
|
||||
#[cfg(target_os = "windows")]
|
||||
cmd.creation_flags(0x08000000);
|
||||
|
||||
let status = match cmd.status() {
|
||||
Ok(s) => s,
|
||||
Err(e) if e.raw_os_error() == Some(13) => {
|
||||
// Permission denied — fix permissions and retry
|
||||
eprintln!("[media] Permission denied on ffmpeg, fixing permissions and retrying...");
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
if let Ok(meta) = std::fs::metadata(&ffmpeg) {
|
||||
let mut perms = meta.permissions();
|
||||
perms.set_mode(0o755);
|
||||
let _ = std::fs::set_permissions(&ffmpeg, perms);
|
||||
}
|
||||
// Also fix ffprobe if it exists
|
||||
let ffprobe = ffmpeg.replace("ffmpeg", "ffprobe");
|
||||
if let Ok(meta) = std::fs::metadata(&ffprobe) {
|
||||
let mut perms = meta.permissions();
|
||||
perms.set_mode(0o755);
|
||||
let _ = std::fs::set_permissions(&ffprobe, perms);
|
||||
}
|
||||
}
|
||||
Command::new(&ffmpeg)
|
||||
.args(["-y", "-i", &file_path, "-vn", "-acodec", "pcm_s16le", "-ar", "22050", "-ac", "1"])
|
||||
.arg(output.to_str().unwrap())
|
||||
.stdout(std::process::Stdio::null())
|
||||
.stderr(std::process::Stdio::piped())
|
||||
.status()
|
||||
.map_err(|e| format!("Failed to run ffmpeg after chmod: {e}"))?
|
||||
}
|
||||
Err(e) => return Err(format!("Failed to run ffmpeg: {e}")),
|
||||
};
|
||||
|
||||
if !status.success() {
|
||||
return Err(format!("ffmpeg exited with status {status}"));
|
||||
}
|
||||
|
||||
if !output.exists() {
|
||||
return Err("ffmpeg completed but output file not found".to_string());
|
||||
}
|
||||
|
||||
eprintln!("[media] Audio extracted successfully");
|
||||
Ok(output.to_string_lossy().to_string())
|
||||
}
|
||||
|
||||
#[tauri::command]
|
||||
pub fn check_file_exists(path: String) -> bool {
|
||||
std::path::Path::new(&path).exists()
|
||||
}
|
||||
|
||||
#[tauri::command]
|
||||
pub fn copy_file(src: String, dst: String) -> Result<(), String> {
|
||||
std::fs::copy(&src, &dst).map_err(|e| format!("Failed to copy file: {e}"))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[tauri::command]
|
||||
pub fn create_dir(path: String) -> Result<(), String> {
|
||||
std::fs::create_dir_all(&path).map_err(|e| format!("Failed to create directory: {e}"))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Find ffmpeg binary — check sidecar directory first, then system PATH.
|
||||
fn find_ffmpeg() -> Option<String> {
|
||||
// Check sidecar extract dir (ffmpeg is bundled with the sidecar)
|
||||
if let Some(data_dir) = crate::sidecar::DATA_DIR.get() {
|
||||
// Read sidecar version to find the right directory
|
||||
let version_file = data_dir.join("sidecar-version.txt");
|
||||
if let Ok(version) = std::fs::read_to_string(&version_file) {
|
||||
let version = version.trim();
|
||||
let sidecar_dir = data_dir.join(format!("sidecar-{version}"));
|
||||
let ffmpeg_name = if cfg!(target_os = "windows") {
|
||||
"ffmpeg.exe"
|
||||
} else {
|
||||
"ffmpeg"
|
||||
};
|
||||
let ffmpeg_path = sidecar_dir.join(ffmpeg_name);
|
||||
if ffmpeg_path.exists() {
|
||||
return Some(ffmpeg_path.to_string_lossy().to_string());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Fall back to system PATH
|
||||
let ffmpeg_name = if cfg!(target_os = "windows") {
|
||||
"ffmpeg.exe"
|
||||
} else {
|
||||
"ffmpeg"
|
||||
};
|
||||
if Command::new(ffmpeg_name)
|
||||
.arg("-version")
|
||||
.stdout(std::process::Stdio::null())
|
||||
.stderr(std::process::Stdio::null())
|
||||
.status()
|
||||
.is_ok()
|
||||
{
|
||||
return Some(ffmpeg_name.to_string());
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
@@ -1,8 +1,6 @@
|
||||
pub mod ai;
|
||||
pub mod export;
|
||||
pub mod media;
|
||||
pub mod project;
|
||||
pub mod settings;
|
||||
pub mod sidecar;
|
||||
pub mod system;
|
||||
pub mod transcribe;
|
||||
|
||||
@@ -12,12 +12,7 @@ use crate::state::AppState;
|
||||
pub struct ProjectFile {
|
||||
pub version: u32,
|
||||
pub name: String,
|
||||
#[serde(default)]
|
||||
pub audio_file: Option<String>,
|
||||
#[serde(default)]
|
||||
pub source_file: Option<String>,
|
||||
#[serde(default)]
|
||||
pub audio_wav: Option<String>,
|
||||
pub audio_file: String,
|
||||
pub created_at: String,
|
||||
pub segments: Vec<ProjectFileSegment>,
|
||||
pub speakers: Vec<ProjectFileSpeaker>,
|
||||
|
||||
@@ -32,16 +32,3 @@ pub fn save_settings(settings: Value) -> Result<(), String> {
|
||||
fs::write(&path, json).map_err(|e| format!("Cannot write settings: {e}"))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Toggle devtools on the main window.
|
||||
#[tauri::command]
|
||||
pub fn toggle_devtools(app: tauri::AppHandle, open: bool) {
|
||||
use tauri::Manager;
|
||||
if let Some(window) = app.get_webview_window("main") {
|
||||
if open {
|
||||
window.open_devtools();
|
||||
} else {
|
||||
window.close_devtools();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,258 +0,0 @@
|
||||
use futures_util::StreamExt;
|
||||
use serde::Serialize;
|
||||
use std::io::Write;
|
||||
use tauri::{AppHandle, Emitter};
|
||||
|
||||
use crate::sidecar::{SidecarManager, DATA_DIR};
|
||||
|
||||
const REPO_API: &str = "https://repo.anhonesthost.net/api/v1/repos/MacroPad/voice-to-notes";
|
||||
|
||||
#[derive(Serialize, Clone)]
|
||||
struct DownloadProgress {
|
||||
downloaded: u64,
|
||||
total: u64,
|
||||
percent: u8,
|
||||
}
|
||||
|
||||
#[derive(Serialize)]
|
||||
pub struct UpdateInfo {
|
||||
pub current_version: String,
|
||||
pub latest_version: String,
|
||||
}
|
||||
|
||||
/// Read the locally installed sidecar version from `sidecar-version.txt`.
|
||||
/// Returns `None` if the file doesn't exist or can't be read.
|
||||
fn read_local_sidecar_version() -> Option<String> {
|
||||
let data_dir = DATA_DIR.get()?;
|
||||
let version_file = data_dir.join("sidecar-version.txt");
|
||||
std::fs::read_to_string(version_file)
|
||||
.ok()
|
||||
.map(|v| v.trim().to_string())
|
||||
.filter(|v| !v.is_empty())
|
||||
}
|
||||
|
||||
/// Write the sidecar version to `sidecar-version.txt` after a successful download.
|
||||
fn write_local_sidecar_version(version: &str) -> Result<(), String> {
|
||||
let data_dir = DATA_DIR.get().ok_or("App data directory not initialized")?;
|
||||
let version_file = data_dir.join("sidecar-version.txt");
|
||||
std::fs::write(&version_file, version)
|
||||
.map_err(|e| format!("Failed to write sidecar version file: {}", e))
|
||||
}
|
||||
|
||||
/// Fetch releases from the Gitea API and find the latest sidecar release
|
||||
/// (one whose tag_name starts with "sidecar-v").
|
||||
async fn fetch_latest_sidecar_release(
|
||||
client: &reqwest::Client,
|
||||
) -> Result<serde_json::Value, String> {
|
||||
let releases_url = format!("{}/releases?limit=20", REPO_API);
|
||||
let resp = client
|
||||
.get(&releases_url)
|
||||
.header("Accept", "application/json")
|
||||
.send()
|
||||
.await
|
||||
.map_err(|e| format!("Failed to fetch releases: {}", e))?;
|
||||
|
||||
if !resp.status().is_success() {
|
||||
return Err(format!("Failed to fetch releases: HTTP {}", resp.status()));
|
||||
}
|
||||
|
||||
let releases = resp
|
||||
.json::<Vec<serde_json::Value>>()
|
||||
.await
|
||||
.map_err(|e| format!("Failed to parse releases JSON: {}", e))?;
|
||||
|
||||
releases
|
||||
.into_iter()
|
||||
.find(|r| {
|
||||
r["tag_name"]
|
||||
.as_str()
|
||||
.map_or(false, |t| t.starts_with("sidecar-v"))
|
||||
})
|
||||
.ok_or_else(|| "No sidecar release found".to_string())
|
||||
}
|
||||
|
||||
/// Extract the version string from a sidecar tag name (e.g. "sidecar-v1.0.1" -> "1.0.1").
|
||||
fn version_from_sidecar_tag(tag: &str) -> &str {
|
||||
tag.strip_prefix("sidecar-v").unwrap_or(tag)
|
||||
}
|
||||
|
||||
/// Check if the sidecar binary exists for the currently installed version.
|
||||
#[tauri::command]
|
||||
pub fn check_sidecar() -> bool {
|
||||
let data_dir = match DATA_DIR.get() {
|
||||
Some(d) => d,
|
||||
None => return false,
|
||||
};
|
||||
|
||||
let version = match read_local_sidecar_version() {
|
||||
Some(v) => v,
|
||||
None => return false,
|
||||
};
|
||||
|
||||
let binary_name = if cfg!(target_os = "windows") {
|
||||
"voice-to-notes-sidecar.exe"
|
||||
} else {
|
||||
"voice-to-notes-sidecar"
|
||||
};
|
||||
|
||||
let extract_dir = data_dir.join(format!("sidecar-{}", version));
|
||||
extract_dir.join(binary_name).exists()
|
||||
}
|
||||
|
||||
/// Determine the current platform name for asset downloads.
|
||||
fn platform_os() -> &'static str {
|
||||
if cfg!(target_os = "windows") {
|
||||
"windows"
|
||||
} else if cfg!(target_os = "macos") {
|
||||
"macos"
|
||||
} else {
|
||||
"linux"
|
||||
}
|
||||
}
|
||||
|
||||
/// Determine the current architecture name for asset downloads.
|
||||
fn platform_arch() -> &'static str {
|
||||
if cfg!(target_arch = "aarch64") {
|
||||
"aarch64"
|
||||
} else {
|
||||
"x86_64"
|
||||
}
|
||||
}
|
||||
|
||||
/// Download the sidecar binary for the given variant (cpu or cuda).
|
||||
#[tauri::command]
|
||||
pub async fn download_sidecar(app: AppHandle, variant: String) -> Result<(), String> {
|
||||
let data_dir = DATA_DIR.get().ok_or("App data directory not initialized")?;
|
||||
|
||||
let os = platform_os();
|
||||
let arch = platform_arch();
|
||||
let asset_name = format!("sidecar-{}-{}-{}.zip", os, arch, variant);
|
||||
|
||||
// Fetch the latest sidecar release from Gitea API
|
||||
let client = reqwest::Client::new();
|
||||
let sidecar_release = fetch_latest_sidecar_release(&client).await?;
|
||||
|
||||
let tag = sidecar_release["tag_name"]
|
||||
.as_str()
|
||||
.ok_or("No tag_name in sidecar release")?;
|
||||
let sidecar_version = version_from_sidecar_tag(tag).to_string();
|
||||
|
||||
// Find the matching asset
|
||||
let assets = sidecar_release["assets"]
|
||||
.as_array()
|
||||
.ok_or("No assets found in sidecar release")?;
|
||||
|
||||
let download_url = assets
|
||||
.iter()
|
||||
.find(|a| a["name"].as_str() == Some(&asset_name))
|
||||
.and_then(|a| a["browser_download_url"].as_str())
|
||||
.ok_or_else(|| {
|
||||
format!(
|
||||
"Asset '{}' not found in sidecar release {}",
|
||||
asset_name, tag
|
||||
)
|
||||
})?
|
||||
.to_string();
|
||||
|
||||
// Stream download with progress events
|
||||
let response: reqwest::Response = client
|
||||
.get(&download_url)
|
||||
.send()
|
||||
.await
|
||||
.map_err(|e| format!("Failed to start download: {}", e))?;
|
||||
|
||||
if !response.status().is_success() {
|
||||
return Err(format!("Download failed: HTTP {}", response.status()));
|
||||
}
|
||||
|
||||
let total: u64 = response.content_length().unwrap_or(0);
|
||||
let mut downloaded: u64 = 0;
|
||||
let mut stream = response.bytes_stream();
|
||||
|
||||
let zip_path = data_dir.join("sidecar.zip");
|
||||
let mut file = std::fs::File::create(&zip_path)
|
||||
.map_err(|e| format!("Failed to create zip file: {}", e))?;
|
||||
|
||||
while let Some(chunk) = stream.next().await {
|
||||
let chunk: bytes::Bytes = chunk.map_err(|e| format!("Download stream error: {}", e))?;
|
||||
file.write_all(&chunk)
|
||||
.map_err(|e| format!("Failed to write chunk: {}", e))?;
|
||||
downloaded += chunk.len() as u64;
|
||||
let percent = if total > 0 {
|
||||
(downloaded * 100 / total) as u8
|
||||
} else {
|
||||
0
|
||||
};
|
||||
let _ = app.emit(
|
||||
"sidecar-download-progress",
|
||||
DownloadProgress {
|
||||
downloaded,
|
||||
total,
|
||||
percent,
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
// Extract the downloaded zip
|
||||
let extract_dir = data_dir.join(format!("sidecar-{}", sidecar_version));
|
||||
SidecarManager::extract_zip(&zip_path, &extract_dir)?;
|
||||
|
||||
// Make all binaries executable on Unix (sidecar, ffmpeg, ffprobe, etc.)
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
if let Ok(entries) = std::fs::read_dir(&extract_dir) {
|
||||
for entry in entries.flatten() {
|
||||
let path = entry.path();
|
||||
if path.is_file() {
|
||||
if let Ok(meta) = std::fs::metadata(&path) {
|
||||
let mut perms = meta.permissions();
|
||||
perms.set_mode(0o755);
|
||||
let _ = std::fs::set_permissions(&path, perms);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Write the sidecar version file
|
||||
write_local_sidecar_version(&sidecar_version)?;
|
||||
|
||||
// Clean up the zip file and old sidecar versions
|
||||
let _ = std::fs::remove_file(&zip_path);
|
||||
SidecarManager::cleanup_old_sidecars(data_dir, &sidecar_version);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Check if a sidecar update is available.
|
||||
#[tauri::command]
|
||||
pub async fn check_sidecar_update() -> Result<Option<UpdateInfo>, String> {
|
||||
// If sidecar doesn't exist yet, return None (first launch handled separately)
|
||||
if !check_sidecar() {
|
||||
return Ok(None);
|
||||
}
|
||||
|
||||
let current_version = match read_local_sidecar_version() {
|
||||
Some(v) => v,
|
||||
None => return Ok(None),
|
||||
};
|
||||
|
||||
// Fetch latest sidecar release from Gitea API
|
||||
let client = reqwest::Client::new();
|
||||
let sidecar_release = fetch_latest_sidecar_release(&client).await?;
|
||||
|
||||
let latest_tag = sidecar_release["tag_name"]
|
||||
.as_str()
|
||||
.ok_or("No tag_name in sidecar release")?;
|
||||
let latest_version = version_from_sidecar_tag(latest_tag);
|
||||
|
||||
if latest_version != current_version {
|
||||
Ok(Some(UpdateInfo {
|
||||
current_version,
|
||||
latest_version: latest_version.to_string(),
|
||||
}))
|
||||
} else {
|
||||
Ok(None)
|
||||
}
|
||||
}
|
||||
@@ -60,18 +60,3 @@ pub fn llama_list_models() -> Value {
|
||||
pub fn get_data_dir() -> String {
|
||||
LlamaManager::data_dir().to_string_lossy().to_string()
|
||||
}
|
||||
|
||||
/// Log a message from the frontend to a file for debugging.
|
||||
#[tauri::command]
|
||||
pub fn log_frontend(level: String, message: String) {
|
||||
use std::io::Write;
|
||||
let log_path = LlamaManager::data_dir().join("frontend.log");
|
||||
if let Ok(mut file) = std::fs::OpenOptions::new()
|
||||
.create(true)
|
||||
.append(true)
|
||||
.open(&log_path)
|
||||
{
|
||||
let timestamp = chrono::Local::now().format("%Y-%m-%d %H:%M:%S");
|
||||
let _ = writeln!(file, "[{timestamp}] [{level}] {message}");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -9,16 +9,12 @@ use tauri::Manager;
|
||||
|
||||
use commands::ai::{ai_chat, ai_configure, ai_list_providers};
|
||||
use commands::export::export_transcript;
|
||||
use commands::media::{check_file_exists, copy_file, create_dir, extract_audio};
|
||||
use commands::project::{
|
||||
create_project, delete_project, get_project, list_projects, load_project_file,
|
||||
load_project_transcript, save_project_file, save_project_transcript, update_segment,
|
||||
};
|
||||
use commands::settings::{load_settings, save_settings, toggle_devtools};
|
||||
use commands::sidecar::{check_sidecar, check_sidecar_update, download_sidecar};
|
||||
use commands::system::{
|
||||
get_data_dir, llama_list_models, llama_start, llama_status, llama_stop, log_frontend,
|
||||
};
|
||||
use commands::settings::{load_settings, save_settings};
|
||||
use commands::system::{get_data_dir, llama_list_models, llama_start, llama_status, llama_stop};
|
||||
use commands::transcribe::{download_diarize_model, run_pipeline, transcribe_file};
|
||||
use state::AppState;
|
||||
|
||||
@@ -31,14 +27,6 @@ pub fn run() {
|
||||
.plugin(tauri_plugin_dialog::init())
|
||||
.manage(app_state)
|
||||
.setup(|app| {
|
||||
// Tell the sidecar manager where Tauri placed bundled resources
|
||||
// and where to extract the sidecar archive
|
||||
if let (Ok(resource_dir), Ok(data_dir)) =
|
||||
(app.path().resource_dir(), app.path().app_local_data_dir())
|
||||
{
|
||||
sidecar::init_dirs(resource_dir, data_dir);
|
||||
}
|
||||
|
||||
// Set the webview background to match the app's dark theme
|
||||
if let Some(window) = app.get_webview_window("main") {
|
||||
let _ = window.set_background_color(Some(Color(10, 10, 35, 255)));
|
||||
@@ -69,15 +57,6 @@ pub fn run() {
|
||||
get_data_dir,
|
||||
load_settings,
|
||||
save_settings,
|
||||
check_sidecar,
|
||||
download_sidecar,
|
||||
check_sidecar_update,
|
||||
log_frontend,
|
||||
toggle_devtools,
|
||||
extract_audio,
|
||||
check_file_exists,
|
||||
copy_file,
|
||||
create_dir,
|
||||
])
|
||||
.run(tauri::generate_context!())
|
||||
.expect("error while running tauri application");
|
||||
|
||||
@@ -2,27 +2,11 @@ pub mod ipc;
|
||||
pub mod messages;
|
||||
|
||||
use std::io::{BufRead, BufReader, Write};
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::process::{Child, ChildStdin, Command, Stdio};
|
||||
use std::sync::{Mutex, OnceLock};
|
||||
|
||||
#[cfg(target_os = "windows")]
|
||||
use std::os::windows::process::CommandExt;
|
||||
|
||||
use crate::sidecar::messages::IPCMessage;
|
||||
|
||||
/// Resource directory set by the Tauri app during setup.
|
||||
static RESOURCE_DIR: OnceLock<PathBuf> = OnceLock::new();
|
||||
/// App data directory for extracting the sidecar archive.
|
||||
pub(crate) static DATA_DIR: OnceLock<PathBuf> = OnceLock::new();
|
||||
|
||||
/// Initialize directories for sidecar resolution.
|
||||
/// Must be called from the Tauri setup before any sidecar operations.
|
||||
pub fn init_dirs(resource_dir: PathBuf, data_dir: PathBuf) {
|
||||
RESOURCE_DIR.set(resource_dir).ok();
|
||||
DATA_DIR.set(data_dir).ok();
|
||||
}
|
||||
|
||||
/// Get the global sidecar manager singleton.
|
||||
pub fn sidecar() -> &'static SidecarManager {
|
||||
static INSTANCE: OnceLock<SidecarManager> = OnceLock::new();
|
||||
@@ -56,203 +40,38 @@ impl SidecarManager {
|
||||
cfg!(debug_assertions) || std::env::var("VOICE_TO_NOTES_DEV").is_ok()
|
||||
}
|
||||
|
||||
/// Read the locally installed sidecar version from `sidecar-version.txt`.
|
||||
fn read_sidecar_version() -> Result<String, String> {
|
||||
let data_dir = DATA_DIR.get().ok_or("App data directory not initialized")?;
|
||||
let version_file = data_dir.join("sidecar-version.txt");
|
||||
std::fs::read_to_string(&version_file)
|
||||
.map_err(|_| {
|
||||
"Sidecar not installed: sidecar-version.txt not found. Please download the sidecar."
|
||||
.to_string()
|
||||
})
|
||||
.map(|v| v.trim().to_string())
|
||||
.and_then(|v| {
|
||||
if v.is_empty() {
|
||||
Err(
|
||||
"Sidecar version file is empty. Please re-download the sidecar."
|
||||
.to_string(),
|
||||
)
|
||||
} else {
|
||||
Ok(v)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
/// Resolve the frozen sidecar binary path (production mode).
|
||||
///
|
||||
/// Reads the installed sidecar version from `sidecar-version.txt` and
|
||||
/// looks for the binary in the corresponding `sidecar-{version}` directory.
|
||||
/// If the version file doesn't exist, the sidecar hasn't been downloaded yet.
|
||||
fn resolve_sidecar_path() -> Result<PathBuf, String> {
|
||||
fn resolve_sidecar_path() -> Result<std::path::PathBuf, String> {
|
||||
let exe = std::env::current_exe().map_err(|e| format!("Cannot get current exe: {e}"))?;
|
||||
let exe_dir = exe
|
||||
.parent()
|
||||
.ok_or_else(|| "Cannot get exe parent directory".to_string())?;
|
||||
|
||||
let binary_name = if cfg!(target_os = "windows") {
|
||||
"voice-to-notes-sidecar.exe"
|
||||
} else {
|
||||
"voice-to-notes-sidecar"
|
||||
};
|
||||
|
||||
let data_dir = DATA_DIR.get().ok_or("App data directory not initialized")?;
|
||||
let current_version = Self::read_sidecar_version()?;
|
||||
let extract_dir = data_dir.join(format!("sidecar-{}", current_version));
|
||||
|
||||
let binary_path = extract_dir.join(binary_name);
|
||||
|
||||
// Already extracted — use it directly
|
||||
if binary_path.exists() {
|
||||
Self::cleanup_old_sidecars(data_dir, ¤t_version);
|
||||
return Ok(binary_path);
|
||||
// Tauri places externalBin next to the app binary
|
||||
let path = exe_dir.join(binary_name);
|
||||
if path.exists() {
|
||||
return Ok(path);
|
||||
}
|
||||
|
||||
// Find sidecar.zip in resource dir or next to exe
|
||||
let zip_path = Self::find_sidecar_zip()?;
|
||||
Self::extract_zip(&zip_path, &extract_dir)?;
|
||||
|
||||
if !binary_path.exists() {
|
||||
return Err(format!(
|
||||
"Sidecar binary not found after extraction at {}",
|
||||
binary_path.display()
|
||||
));
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
Self::set_executable_permissions(&extract_dir);
|
||||
|
||||
Self::cleanup_old_sidecars(data_dir, ¤t_version);
|
||||
Ok(binary_path)
|
||||
}
|
||||
|
||||
/// Locate the bundled sidecar.zip archive.
|
||||
fn find_sidecar_zip() -> Result<PathBuf, String> {
|
||||
let mut candidates: Vec<PathBuf> = Vec::new();
|
||||
|
||||
if let Some(resource_dir) = RESOURCE_DIR.get() {
|
||||
candidates.push(resource_dir.join("sidecar.zip"));
|
||||
}
|
||||
if let Ok(exe) = std::env::current_exe() {
|
||||
if let Some(exe_dir) = exe.parent() {
|
||||
candidates.push(exe_dir.join("sidecar.zip"));
|
||||
}
|
||||
}
|
||||
|
||||
for path in &candidates {
|
||||
if path.exists() {
|
||||
return Ok(path.clone());
|
||||
}
|
||||
// Also check inside a subdirectory (onedir PyInstaller output)
|
||||
let subdir_path = exe_dir.join("voice-to-notes-sidecar").join(binary_name);
|
||||
if subdir_path.exists() {
|
||||
return Ok(subdir_path);
|
||||
}
|
||||
|
||||
Err(format!(
|
||||
"Sidecar archive not found. Checked:\n{}",
|
||||
candidates
|
||||
.iter()
|
||||
.map(|p| format!(" {}", p.display()))
|
||||
.collect::<Vec<_>>()
|
||||
.join("\n"),
|
||||
"Sidecar binary not found. Looked for:\n {}\n {}",
|
||||
path.display(),
|
||||
subdir_path.display(),
|
||||
))
|
||||
}
|
||||
|
||||
/// Extract a zip archive to the given directory.
|
||||
pub(crate) fn extract_zip(zip_path: &Path, dest: &Path) -> Result<(), String> {
|
||||
eprintln!(
|
||||
"[sidecar-rs] Extracting sidecar from {} to {}",
|
||||
zip_path.display(),
|
||||
dest.display()
|
||||
);
|
||||
|
||||
// Clean destination so we don't mix old and new files
|
||||
if dest.exists() {
|
||||
std::fs::remove_dir_all(dest)
|
||||
.map_err(|e| format!("Failed to clean extraction dir: {e}"))?;
|
||||
}
|
||||
std::fs::create_dir_all(dest)
|
||||
.map_err(|e| format!("Failed to create extraction dir: {e}"))?;
|
||||
|
||||
let file =
|
||||
std::fs::File::open(zip_path).map_err(|e| format!("Cannot open sidecar zip: {e}"))?;
|
||||
let mut archive =
|
||||
zip::ZipArchive::new(file).map_err(|e| format!("Invalid sidecar zip: {e}"))?;
|
||||
|
||||
for i in 0..archive.len() {
|
||||
let mut entry = archive
|
||||
.by_index(i)
|
||||
.map_err(|e| format!("Zip entry error: {e}"))?;
|
||||
|
||||
let name = entry.name().to_string();
|
||||
let outpath = dest.join(&name);
|
||||
|
||||
if entry.is_dir() {
|
||||
std::fs::create_dir_all(&outpath)
|
||||
.map_err(|e| format!("Cannot create dir {}: {e}", outpath.display()))?;
|
||||
} else {
|
||||
if let Some(parent) = outpath.parent() {
|
||||
std::fs::create_dir_all(parent)
|
||||
.map_err(|e| format!("Cannot create dir {}: {e}", parent.display()))?;
|
||||
}
|
||||
let mut outfile = std::fs::File::create(&outpath)
|
||||
.map_err(|e| format!("Cannot create {}: {e}", outpath.display()))?;
|
||||
std::io::copy(&mut entry, &mut outfile)
|
||||
.map_err(|e| format!("Write error for {}: {e}", name))?;
|
||||
}
|
||||
}
|
||||
|
||||
eprintln!("[sidecar-rs] Sidecar extracted successfully");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Remove old sidecar-* directories that don't match the current version.
|
||||
/// Called after the current version's sidecar is confirmed ready.
|
||||
/// Set execute permissions on all files in a directory (Unix only).
|
||||
#[cfg(unix)]
|
||||
fn set_executable_permissions(dir: &Path) {
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
if let Ok(entries) = std::fs::read_dir(dir) {
|
||||
for entry in entries.flatten() {
|
||||
let path = entry.path();
|
||||
if path.is_file() {
|
||||
if let Ok(meta) = std::fs::metadata(&path) {
|
||||
let mut perms = meta.permissions();
|
||||
perms.set_mode(0o755);
|
||||
let _ = std::fs::set_permissions(&path, perms);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) fn cleanup_old_sidecars(data_dir: &Path, current_version: &str) {
|
||||
let current_dir_name = format!("sidecar-{}", current_version);
|
||||
|
||||
let entries = match std::fs::read_dir(data_dir) {
|
||||
Ok(entries) => entries,
|
||||
Err(e) => {
|
||||
eprintln!("[sidecar-rs] Cannot read data dir for cleanup: {e}");
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
for entry in entries.flatten() {
|
||||
let name = entry.file_name();
|
||||
let name_str = name.to_string_lossy();
|
||||
|
||||
if !name_str.starts_with("sidecar-") {
|
||||
continue;
|
||||
}
|
||||
if *name_str == current_dir_name {
|
||||
continue;
|
||||
}
|
||||
if entry.path().is_dir() {
|
||||
eprintln!(
|
||||
"[sidecar-rs] Removing old sidecar: {}",
|
||||
entry.path().display()
|
||||
);
|
||||
if let Err(e) = std::fs::remove_dir_all(entry.path()) {
|
||||
eprintln!(
|
||||
"[sidecar-rs] Failed to remove {}: {e}",
|
||||
entry.path().display()
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Find a working Python command for the current platform.
|
||||
fn find_python_command() -> &'static str {
|
||||
if cfg!(target_os = "windows") {
|
||||
@@ -295,8 +114,15 @@ impl SidecarManager {
|
||||
if Self::is_dev_mode() {
|
||||
self.start_python_dev()
|
||||
} else {
|
||||
let path = Self::resolve_sidecar_path()?;
|
||||
self.start_binary(&path)
|
||||
match Self::resolve_sidecar_path() {
|
||||
Ok(path) => self.start_binary(&path),
|
||||
Err(e) => {
|
||||
eprintln!(
|
||||
"[sidecar-rs] Frozen binary not found ({e}), falling back to dev mode"
|
||||
);
|
||||
self.start_python_dev()
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -305,66 +131,15 @@ impl SidecarManager {
|
||||
self.stop().ok();
|
||||
eprintln!("[sidecar-rs] Starting frozen sidecar: {}", path.display());
|
||||
|
||||
// Log sidecar stderr to a file for diagnostics
|
||||
let stderr_cfg = if let Some(data_dir) = DATA_DIR.get() {
|
||||
let _ = std::fs::create_dir_all(data_dir);
|
||||
let log_path = data_dir.join("sidecar.log");
|
||||
eprintln!("[sidecar-rs] Sidecar stderr → {}", log_path.display());
|
||||
match std::fs::File::create(&log_path) {
|
||||
Ok(f) => Stdio::from(f),
|
||||
Err(e) => {
|
||||
eprintln!("[sidecar-rs] Failed to create sidecar.log: {e}");
|
||||
Stdio::inherit()
|
||||
}
|
||||
}
|
||||
} else {
|
||||
eprintln!("[sidecar-rs] DATA_DIR not set, sidecar stderr will not be logged");
|
||||
Stdio::inherit()
|
||||
};
|
||||
|
||||
let mut cmd = Command::new(path);
|
||||
cmd.stdin(Stdio::piped())
|
||||
let child = Command::new(path)
|
||||
.stdin(Stdio::piped())
|
||||
.stdout(Stdio::piped())
|
||||
.stderr(stderr_cfg);
|
||||
.stderr(Stdio::inherit())
|
||||
.spawn()
|
||||
.map_err(|e| format!("Failed to start sidecar binary: {e}"))?;
|
||||
|
||||
// Hide the console window on Windows (CREATE_NO_WINDOW = 0x08000000)
|
||||
#[cfg(target_os = "windows")]
|
||||
cmd.creation_flags(0x08000000);
|
||||
|
||||
match cmd.spawn() {
|
||||
Ok(child) => {
|
||||
self.attach(child)?;
|
||||
self.wait_for_ready()
|
||||
}
|
||||
Err(e) if e.raw_os_error() == Some(13) => {
|
||||
// Permission denied — fix permissions and retry once
|
||||
eprintln!("[sidecar-rs] Permission denied, fixing permissions and retrying...");
|
||||
#[cfg(unix)]
|
||||
if let Some(dir) = path.parent() {
|
||||
Self::set_executable_permissions(dir);
|
||||
}
|
||||
let mut retry_cmd = Command::new(path);
|
||||
retry_cmd
|
||||
.stdin(Stdio::piped())
|
||||
.stdout(Stdio::piped())
|
||||
.stderr(if let Some(data_dir) = DATA_DIR.get() {
|
||||
let log_path = data_dir.join("sidecar.log");
|
||||
std::fs::File::create(&log_path)
|
||||
.map(Stdio::from)
|
||||
.unwrap_or_else(|_| Stdio::inherit())
|
||||
} else {
|
||||
Stdio::inherit()
|
||||
});
|
||||
#[cfg(target_os = "windows")]
|
||||
retry_cmd.creation_flags(0x08000000);
|
||||
let child = retry_cmd
|
||||
.spawn()
|
||||
.map_err(|e| format!("Failed to start sidecar binary after chmod: {e}"))?;
|
||||
self.attach(child)?;
|
||||
self.wait_for_ready()
|
||||
}
|
||||
Err(e) => Err(format!("Failed to start sidecar binary: {e}")),
|
||||
}
|
||||
self.attach(child)?;
|
||||
self.wait_for_ready()
|
||||
}
|
||||
|
||||
/// Spawn the Python sidecar in dev mode (system Python).
|
||||
@@ -425,22 +200,7 @@ impl SidecarManager {
|
||||
.read_line(&mut line)
|
||||
.map_err(|e| format!("Read error: {e}"))?;
|
||||
if bytes == 0 {
|
||||
// Try to get the exit code for diagnostics
|
||||
let exit_info = {
|
||||
let mut proc = self.process.lock().map_err(|e| e.to_string())?;
|
||||
if let Some(ref mut child) = *proc {
|
||||
match child.try_wait() {
|
||||
Ok(Some(status)) => format!(" (exit status: {status})"),
|
||||
_ => String::new(),
|
||||
}
|
||||
} else {
|
||||
String::new()
|
||||
}
|
||||
};
|
||||
return Err(format!(
|
||||
"Sidecar closed stdout before sending ready{exit_info}. \
|
||||
The Python sidecar may have crashed on startup — check app logs for details."
|
||||
));
|
||||
return Err("Sidecar closed stdout before sending ready".to_string());
|
||||
}
|
||||
let trimmed = line.trim();
|
||||
if trimmed.is_empty() {
|
||||
@@ -470,46 +230,11 @@ impl SidecarManager {
|
||||
|
||||
/// Send a message and receive the response, calling a callback for intermediate messages.
|
||||
/// Intermediate messages include progress, pipeline.segment, and pipeline.speaker_update.
|
||||
///
|
||||
/// If the sidecar has crashed (broken pipe), automatically restarts it and retries once.
|
||||
pub fn send_and_receive_with_progress<F>(
|
||||
&self,
|
||||
msg: &IPCMessage,
|
||||
on_intermediate: F,
|
||||
) -> Result<IPCMessage, String>
|
||||
where
|
||||
F: Fn(&IPCMessage),
|
||||
{
|
||||
match self.send_and_receive_inner(msg, &on_intermediate) {
|
||||
Ok(response) => Ok(response),
|
||||
Err(e)
|
||||
if e.contains("Write error")
|
||||
|| e.contains("closed stdout")
|
||||
|| e.contains("not available") =>
|
||||
{
|
||||
eprintln!("[sidecar-rs] Sidecar communication failed ({e}), restarting...");
|
||||
self.cleanup_handles();
|
||||
// Stop any zombie process
|
||||
{
|
||||
let mut proc = self.process.lock().map_err(|e| e.to_string())?;
|
||||
if let Some(ref mut child) = proc.take() {
|
||||
let _ = child.kill();
|
||||
let _ = child.wait();
|
||||
}
|
||||
}
|
||||
self.ensure_running()?;
|
||||
self.send_and_receive_inner(msg, &on_intermediate)
|
||||
}
|
||||
Err(e) => Err(e),
|
||||
}
|
||||
}
|
||||
|
||||
/// Inner implementation of send_and_receive.
|
||||
fn send_and_receive_inner<F>(
|
||||
&self,
|
||||
msg: &IPCMessage,
|
||||
on_intermediate: &F,
|
||||
) -> Result<IPCMessage, String>
|
||||
where
|
||||
F: Fn(&IPCMessage),
|
||||
{
|
||||
@@ -595,39 +320,8 @@ impl SidecarManager {
|
||||
}
|
||||
|
||||
pub fn is_running(&self) -> bool {
|
||||
let mut proc = match self.process.lock() {
|
||||
Ok(p) => p,
|
||||
Err(_) => return false,
|
||||
};
|
||||
if let Some(ref mut child) = *proc {
|
||||
// Check if the process has exited
|
||||
match child.try_wait() {
|
||||
Ok(Some(_status)) => {
|
||||
// Process has exited — clean up handles
|
||||
eprintln!("[sidecar-rs] Sidecar process has exited");
|
||||
drop(proc);
|
||||
let _ = self.cleanup_handles();
|
||||
false
|
||||
}
|
||||
Ok(None) => true, // Still running
|
||||
Err(_) => false,
|
||||
}
|
||||
} else {
|
||||
false
|
||||
}
|
||||
}
|
||||
|
||||
/// Clean up stdin/stdout/process handles after the sidecar has exited.
|
||||
fn cleanup_handles(&self) {
|
||||
if let Ok(mut s) = self.stdin.lock() {
|
||||
*s = None;
|
||||
}
|
||||
if let Ok(mut r) = self.reader.lock() {
|
||||
*r = None;
|
||||
}
|
||||
if let Ok(mut p) = self.process.lock() {
|
||||
*p = None;
|
||||
}
|
||||
let proc = self.process.lock().ok();
|
||||
proc.map_or(false, |p| p.is_some())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"$schema": "https://schema.tauri.app/config/2",
|
||||
"productName": "Voice to Notes",
|
||||
"version": "0.2.46",
|
||||
"version": "0.1.0",
|
||||
"identifier": "com.voicetonotes.app",
|
||||
"build": {
|
||||
"beforeDevCommand": "npm run dev",
|
||||
@@ -22,7 +22,7 @@
|
||||
}
|
||||
],
|
||||
"security": {
|
||||
"csp": "default-src 'self' http://tauri.localhost; connect-src ipc: http://ipc.localhost http://asset.localhost https://asset.localhost blob:; img-src 'self' asset: http://asset.localhost https://asset.localhost blob:; media-src 'self' asset: http://asset.localhost https://asset.localhost blob:; style-src 'self' 'unsafe-inline'",
|
||||
"csp": "default-src 'self'; img-src 'self' asset: https://asset.localhost; media-src 'self' asset: https://asset.localhost; style-src 'self' 'unsafe-inline'",
|
||||
"assetProtocol": {
|
||||
"enable": true,
|
||||
"scope": ["**"]
|
||||
@@ -31,7 +31,7 @@
|
||||
},
|
||||
"bundle": {
|
||||
"active": true,
|
||||
"targets": ["deb", "rpm", "nsis", "msi", "dmg"],
|
||||
"targets": "all",
|
||||
"icon": [
|
||||
"icons/32x32.png",
|
||||
"icons/128x128.png",
|
||||
@@ -42,18 +42,17 @@
|
||||
"category": "Utility",
|
||||
"shortDescription": "Transcribe audio/video with speaker identification",
|
||||
"longDescription": "Voice to Notes is a desktop application that transcribes audio and video recordings with speaker identification, synchronized playback, and AI-powered analysis. Export to SRT, WebVTT, ASS captions, or plain text.",
|
||||
"resources": [],
|
||||
"copyright": "Voice to Notes Contributors",
|
||||
"license": "MIT",
|
||||
"linux": {
|
||||
"deb": {
|
||||
"depends": []
|
||||
},
|
||||
"appimage": {
|
||||
"bundleMediaFramework": true
|
||||
}
|
||||
},
|
||||
"windows": {
|
||||
"nsis": {
|
||||
"installerHooks": "nsis-hooks.nsh"
|
||||
},
|
||||
"wix": {
|
||||
"language": "en-US"
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
<script lang="ts">
|
||||
import { invoke } from '@tauri-apps/api/core';
|
||||
import { segments, speakers } from '$lib/stores/transcript';
|
||||
import { settings, configureAIProvider } from '$lib/stores/settings';
|
||||
import { settings } from '$lib/stores/settings';
|
||||
|
||||
interface ChatMessage {
|
||||
role: 'user' | 'assistant';
|
||||
@@ -45,12 +45,22 @@
|
||||
}));
|
||||
|
||||
// Ensure the provider is configured with current credentials before chatting
|
||||
await configureAIProvider($settings);
|
||||
const s = $settings;
|
||||
const configMap: Record<string, Record<string, string>> = {
|
||||
openai: { api_key: s.openai_api_key, model: s.openai_model },
|
||||
anthropic: { api_key: s.anthropic_api_key, model: s.anthropic_model },
|
||||
litellm: { api_key: s.litellm_api_key, api_base: s.litellm_api_base, model: s.litellm_model },
|
||||
local: { model: s.local_model_path, base_url: 'http://localhost:8080' },
|
||||
};
|
||||
const config = configMap[s.ai_provider];
|
||||
if (config) {
|
||||
await invoke('ai_configure', { provider: s.ai_provider, config });
|
||||
}
|
||||
|
||||
const result = await invoke<{ response: string }>('ai_chat', {
|
||||
messages: chatMessages,
|
||||
transcriptContext: getTranscriptContext(),
|
||||
provider: $settings.ai_provider,
|
||||
provider: s.ai_provider,
|
||||
});
|
||||
|
||||
messages = [...messages, { role: 'assistant', content: result.response }];
|
||||
|
||||
@@ -4,25 +4,9 @@
|
||||
percent?: number;
|
||||
stage?: string;
|
||||
message?: string;
|
||||
onCancel?: () => void;
|
||||
}
|
||||
|
||||
let { visible = false, percent = 0, stage = '', message = '', onCancel }: Props = $props();
|
||||
|
||||
let showConfirm = $state(false);
|
||||
|
||||
function handleCancelClick() {
|
||||
showConfirm = true;
|
||||
}
|
||||
|
||||
function confirmCancel() {
|
||||
showConfirm = false;
|
||||
onCancel?.();
|
||||
}
|
||||
|
||||
function dismissCancel() {
|
||||
showConfirm = false;
|
||||
}
|
||||
let { visible = false, percent = 0, stage = '', message = '' }: Props = $props();
|
||||
|
||||
// Pipeline steps in order
|
||||
const pipelineSteps = [
|
||||
@@ -105,20 +89,6 @@
|
||||
|
||||
<p class="status-text">{message || 'Please wait...'}</p>
|
||||
<p class="hint-text">This may take several minutes for large files</p>
|
||||
|
||||
{#if onCancel && !showConfirm}
|
||||
<button class="cancel-btn" onclick={handleCancelClick}>Cancel</button>
|
||||
{/if}
|
||||
|
||||
{#if showConfirm}
|
||||
<div class="confirm-box">
|
||||
<p class="confirm-text">Processing is incomplete. If you cancel now, the transcription will need to be started over.</p>
|
||||
<div class="confirm-actions">
|
||||
<button class="confirm-keep" onclick={dismissCancel}>Continue Processing</button>
|
||||
<button class="confirm-cancel" onclick={confirmCancel}>Cancel Processing</button>
|
||||
</div>
|
||||
</div>
|
||||
{/if}
|
||||
</div>
|
||||
</div>
|
||||
{/if}
|
||||
@@ -204,62 +174,4 @@
|
||||
font-size: 0.75rem;
|
||||
color: #555;
|
||||
}
|
||||
.cancel-btn {
|
||||
margin-top: 1.25rem;
|
||||
width: 100%;
|
||||
padding: 0.5rem;
|
||||
background: none;
|
||||
border: 1px solid #4a5568;
|
||||
color: #999;
|
||||
border-radius: 6px;
|
||||
cursor: pointer;
|
||||
font-size: 0.85rem;
|
||||
}
|
||||
.cancel-btn:hover {
|
||||
color: #e0e0e0;
|
||||
border-color: #e94560;
|
||||
}
|
||||
.confirm-box {
|
||||
margin-top: 1.25rem;
|
||||
padding: 0.75rem;
|
||||
background: rgba(233, 69, 96, 0.08);
|
||||
border: 1px solid #e94560;
|
||||
border-radius: 6px;
|
||||
}
|
||||
.confirm-text {
|
||||
margin: 0 0 0.75rem;
|
||||
font-size: 0.8rem;
|
||||
color: #e0e0e0;
|
||||
line-height: 1.4;
|
||||
}
|
||||
.confirm-actions {
|
||||
display: flex;
|
||||
gap: 0.5rem;
|
||||
}
|
||||
.confirm-keep {
|
||||
flex: 1;
|
||||
padding: 0.4rem;
|
||||
background: #0f3460;
|
||||
border: 1px solid #4a5568;
|
||||
color: #e0e0e0;
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
font-size: 0.8rem;
|
||||
}
|
||||
.confirm-keep:hover {
|
||||
background: #1a4a7a;
|
||||
}
|
||||
.confirm-cancel {
|
||||
flex: 1;
|
||||
padding: 0.4rem;
|
||||
background: #e94560;
|
||||
border: none;
|
||||
color: white;
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
font-size: 0.8rem;
|
||||
}
|
||||
.confirm-cancel:hover {
|
||||
background: #d63851;
|
||||
}
|
||||
</style>
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
let { visible, onClose }: Props = $props();
|
||||
|
||||
let localSettings = $state<AppSettings>({ ...$settings });
|
||||
let activeTab = $state<'transcription' | 'speakers' | 'ai' | 'debug'>('transcription');
|
||||
let activeTab = $state<'transcription' | 'speakers' | 'ai' | 'local'>('transcription');
|
||||
let modelStatus = $state<'idle' | 'downloading' | 'success' | 'error'>('idle');
|
||||
let modelError = $state('');
|
||||
let revealedFields = $state<Set<string>>(new Set());
|
||||
@@ -81,8 +81,8 @@
|
||||
<button class="tab" class:active={activeTab === 'ai'} onclick={() => activeTab = 'ai'}>
|
||||
AI Provider
|
||||
</button>
|
||||
<button class="tab" class:active={activeTab === 'debug'} onclick={() => activeTab = 'debug'}>
|
||||
Debug
|
||||
<button class="tab" class:active={activeTab === 'local'} onclick={() => activeTab = 'local'}>
|
||||
Local AI
|
||||
</button>
|
||||
</div>
|
||||
|
||||
@@ -181,27 +181,14 @@
|
||||
<div class="field">
|
||||
<label for="ai-provider">AI Provider</label>
|
||||
<select id="ai-provider" bind:value={localSettings.ai_provider}>
|
||||
<option value="local">Ollama</option>
|
||||
<option value="local">Local (llama-server)</option>
|
||||
<option value="openai">OpenAI</option>
|
||||
<option value="anthropic">Anthropic</option>
|
||||
<option value="litellm">OpenAI Compatible</option>
|
||||
</select>
|
||||
</div>
|
||||
|
||||
{#if localSettings.ai_provider === 'local'}
|
||||
<div class="field">
|
||||
<label for="ollama-url">Ollama URL</label>
|
||||
<input id="ollama-url" type="text" bind:value={localSettings.ollama_url} placeholder="http://localhost:11434" />
|
||||
</div>
|
||||
<div class="field">
|
||||
<label for="ollama-model">Model</label>
|
||||
<input id="ollama-model" type="text" bind:value={localSettings.ollama_model} placeholder="llama3.2" />
|
||||
</div>
|
||||
<p class="hint">
|
||||
Install Ollama from ollama.com, then pull a model with <code>ollama pull llama3.2</code>.
|
||||
The app connects via Ollama's OpenAI-compatible API.
|
||||
</p>
|
||||
{:else if localSettings.ai_provider === 'openai'}
|
||||
{#if localSettings.ai_provider === 'openai'}
|
||||
<div class="field">
|
||||
<label for="openai-key">OpenAI API Key</label>
|
||||
<div class="input-reveal">
|
||||
@@ -242,21 +229,19 @@
|
||||
<input id="litellm-model" type="text" bind:value={localSettings.litellm_model} placeholder="provider/model-name" />
|
||||
</div>
|
||||
{/if}
|
||||
{:else if activeTab === 'debug'}
|
||||
<div class="field checkbox">
|
||||
<label>
|
||||
<input
|
||||
type="checkbox"
|
||||
checked={localSettings.devtools_enabled}
|
||||
onchange={async (e) => {
|
||||
localSettings.devtools_enabled = (e.target as HTMLInputElement).checked;
|
||||
await invoke('toggle_devtools', { open: localSettings.devtools_enabled });
|
||||
}}
|
||||
/>
|
||||
Enable Developer Tools
|
||||
</label>
|
||||
<p class="hint">Opens the browser inspector for debugging. Changes take effect immediately.</p>
|
||||
{:else}
|
||||
<div class="field">
|
||||
<label for="llama-binary">llama-server Binary Path</label>
|
||||
<input id="llama-binary" type="text" bind:value={localSettings.local_binary_path} placeholder="llama-server" />
|
||||
</div>
|
||||
<div class="field">
|
||||
<label for="llama-model">GGUF Model Path</label>
|
||||
<input id="llama-model" type="text" bind:value={localSettings.local_model_path} placeholder="~/.voicetonotes/models/model.gguf" />
|
||||
</div>
|
||||
<p class="hint">
|
||||
Place GGUF model files in ~/.voicetonotes/models/ for auto-detection.
|
||||
The local AI server uses the OpenAI-compatible API from llama.cpp.
|
||||
</p>
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
|
||||
@@ -1,320 +0,0 @@
|
||||
<script lang="ts">
|
||||
import { invoke } from '@tauri-apps/api/core';
|
||||
import { listen } from '@tauri-apps/api/event';
|
||||
import type { UnlistenFn } from '@tauri-apps/api/event';
|
||||
import { onMount } from 'svelte';
|
||||
|
||||
interface Props {
|
||||
onComplete: () => void;
|
||||
}
|
||||
|
||||
let { onComplete }: Props = $props();
|
||||
|
||||
let variant = $state<'cpu' | 'cuda'>('cpu');
|
||||
let downloading = $state(false);
|
||||
let downloadProgress = $state({ downloaded: 0, total: 0, percent: 0 });
|
||||
let error = $state('');
|
||||
let success = $state(false);
|
||||
|
||||
let unlisten: UnlistenFn | null = null;
|
||||
|
||||
onMount(() => {
|
||||
return () => {
|
||||
unlisten?.();
|
||||
};
|
||||
});
|
||||
|
||||
function formatBytes(bytes: number): string {
|
||||
if (bytes < 1024 * 1024) return `${(bytes / 1024).toFixed(0)} KB`;
|
||||
if (bytes < 1024 * 1024 * 1024) return `${(bytes / (1024 * 1024)).toFixed(0)} MB`;
|
||||
return `${(bytes / (1024 * 1024 * 1024)).toFixed(1)} GB`;
|
||||
}
|
||||
|
||||
async function startDownload() {
|
||||
downloading = true;
|
||||
error = '';
|
||||
success = false;
|
||||
|
||||
unlisten = await listen<{ downloaded: number; total: number; percent: number }>(
|
||||
'sidecar-download-progress',
|
||||
(event) => {
|
||||
downloadProgress = event.payload;
|
||||
}
|
||||
);
|
||||
|
||||
try {
|
||||
await invoke('download_sidecar', { variant });
|
||||
success = true;
|
||||
// Brief pause so the user sees "Complete" before the screen goes away
|
||||
setTimeout(() => {
|
||||
onComplete();
|
||||
}, 800);
|
||||
} catch (err) {
|
||||
error = String(err);
|
||||
} finally {
|
||||
downloading = false;
|
||||
unlisten?.();
|
||||
unlisten = null;
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
<div class="setup-overlay">
|
||||
<div class="setup-card">
|
||||
<h1 class="app-title">Voice to Notes</h1>
|
||||
<h2 class="setup-heading">First-Time Setup</h2>
|
||||
<p class="setup-description">
|
||||
Voice to Notes needs to download its AI engine to transcribe audio.
|
||||
</p>
|
||||
|
||||
{#if !downloading && !success}
|
||||
<div class="variant-options">
|
||||
<label class="variant-option" class:selected={variant === 'cpu'}>
|
||||
<input type="radio" name="variant" value="cpu" bind:group={variant} />
|
||||
<div class="variant-info">
|
||||
<span class="variant-label">Standard (CPU)</span>
|
||||
<span class="variant-desc">Works on all computers (~500 MB download)</span>
|
||||
</div>
|
||||
</label>
|
||||
<label class="variant-option" class:selected={variant === 'cuda'}>
|
||||
<input type="radio" name="variant" value="cuda" bind:group={variant} />
|
||||
<div class="variant-info">
|
||||
<span class="variant-label">GPU Accelerated (CUDA)</span>
|
||||
<span class="variant-desc">Faster transcription with NVIDIA GPU (~2 GB download)</span>
|
||||
</div>
|
||||
</label>
|
||||
</div>
|
||||
|
||||
{#if error}
|
||||
<div class="error-box">
|
||||
<p class="error-text">{error}</p>
|
||||
<button class="btn-retry" onclick={startDownload}>Retry</button>
|
||||
</div>
|
||||
{:else}
|
||||
<button class="btn-download" onclick={startDownload}>
|
||||
Download & Install
|
||||
</button>
|
||||
{/if}
|
||||
{:else if downloading}
|
||||
<div class="progress-section">
|
||||
<div class="progress-bar-track">
|
||||
<div class="progress-bar-fill" style="width: {downloadProgress.percent}%"></div>
|
||||
</div>
|
||||
<p class="progress-text">
|
||||
{downloadProgress.percent}% — {formatBytes(downloadProgress.downloaded)} / {formatBytes(downloadProgress.total)}
|
||||
</p>
|
||||
<p class="progress-hint">Downloading {variant === 'cuda' ? 'GPU' : 'CPU'} engine...</p>
|
||||
</div>
|
||||
{:else if success}
|
||||
<div class="success-section">
|
||||
<div class="success-icon">✓</div>
|
||||
<p class="success-text">Setup complete!</p>
|
||||
</div>
|
||||
{/if}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<style>
|
||||
.setup-overlay {
|
||||
position: fixed;
|
||||
inset: 0;
|
||||
background: #0a0a23;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
z-index: 10000;
|
||||
}
|
||||
|
||||
.setup-card {
|
||||
background: #16213e;
|
||||
border: 1px solid #2a3a5e;
|
||||
border-radius: 12px;
|
||||
padding: 2.5rem 3rem;
|
||||
max-width: 480px;
|
||||
width: 90vw;
|
||||
color: #e0e0e0;
|
||||
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
.app-title {
|
||||
font-size: 1.8rem;
|
||||
margin: 0 0 0.25rem;
|
||||
color: #e94560;
|
||||
font-weight: 700;
|
||||
}
|
||||
|
||||
.setup-heading {
|
||||
font-size: 1.1rem;
|
||||
margin: 0 0 0.75rem;
|
||||
color: #e0e0e0;
|
||||
font-weight: 500;
|
||||
}
|
||||
|
||||
.setup-description {
|
||||
font-size: 0.9rem;
|
||||
color: #b0b0b0;
|
||||
margin: 0 0 1.5rem;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
.variant-options {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 0.75rem;
|
||||
margin-bottom: 1.5rem;
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
.variant-option {
|
||||
display: flex;
|
||||
align-items: flex-start;
|
||||
gap: 0.75rem;
|
||||
padding: 0.85rem 1rem;
|
||||
border: 1px solid #2a3a5e;
|
||||
border-radius: 8px;
|
||||
cursor: pointer;
|
||||
transition: border-color 0.15s, background 0.15s;
|
||||
}
|
||||
|
||||
.variant-option:hover {
|
||||
border-color: #4a5568;
|
||||
background: rgba(255, 255, 255, 0.02);
|
||||
}
|
||||
|
||||
.variant-option.selected {
|
||||
border-color: #e94560;
|
||||
background: rgba(233, 69, 96, 0.08);
|
||||
}
|
||||
|
||||
.variant-option input[type='radio'] {
|
||||
margin-top: 0.2rem;
|
||||
accent-color: #e94560;
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.variant-info {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 0.2rem;
|
||||
}
|
||||
|
||||
.variant-label {
|
||||
font-size: 0.9rem;
|
||||
font-weight: 500;
|
||||
color: #e0e0e0;
|
||||
}
|
||||
|
||||
.variant-desc {
|
||||
font-size: 0.78rem;
|
||||
color: #888;
|
||||
}
|
||||
|
||||
.btn-download {
|
||||
background: #e94560;
|
||||
border: none;
|
||||
color: white;
|
||||
padding: 0.7rem 1.5rem;
|
||||
border-radius: 6px;
|
||||
cursor: pointer;
|
||||
font-size: 0.9rem;
|
||||
font-weight: 500;
|
||||
width: 100%;
|
||||
transition: background 0.15s;
|
||||
}
|
||||
|
||||
.btn-download:hover {
|
||||
background: #d63851;
|
||||
}
|
||||
|
||||
.progress-section {
|
||||
margin-top: 0.5rem;
|
||||
}
|
||||
|
||||
.progress-bar-track {
|
||||
width: 100%;
|
||||
height: 8px;
|
||||
background: #1a1a2e;
|
||||
border-radius: 4px;
|
||||
overflow: hidden;
|
||||
border: 1px solid #2a3a5e;
|
||||
}
|
||||
|
||||
.progress-bar-fill {
|
||||
height: 100%;
|
||||
background: #e94560;
|
||||
border-radius: 4px;
|
||||
transition: width 0.3s ease;
|
||||
}
|
||||
|
||||
.progress-text {
|
||||
margin: 0.75rem 0 0;
|
||||
font-size: 0.85rem;
|
||||
color: #e0e0e0;
|
||||
font-variant-numeric: tabular-nums;
|
||||
}
|
||||
|
||||
.progress-hint {
|
||||
margin: 0.35rem 0 0;
|
||||
font-size: 0.78rem;
|
||||
color: #888;
|
||||
}
|
||||
|
||||
.error-box {
|
||||
background: rgba(233, 69, 96, 0.1);
|
||||
border: 1px solid rgba(233, 69, 96, 0.3);
|
||||
border-radius: 8px;
|
||||
padding: 1rem;
|
||||
}
|
||||
|
||||
.error-text {
|
||||
color: #e94560;
|
||||
font-size: 0.85rem;
|
||||
margin: 0 0 0.75rem;
|
||||
word-break: break-word;
|
||||
line-height: 1.4;
|
||||
}
|
||||
|
||||
.btn-retry {
|
||||
background: #e94560;
|
||||
border: none;
|
||||
color: white;
|
||||
padding: 0.5rem 1.25rem;
|
||||
border-radius: 6px;
|
||||
cursor: pointer;
|
||||
font-size: 0.85rem;
|
||||
font-weight: 500;
|
||||
}
|
||||
|
||||
.btn-retry:hover {
|
||||
background: #d63851;
|
||||
}
|
||||
|
||||
.success-section {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
gap: 0.5rem;
|
||||
padding: 1rem 0;
|
||||
}
|
||||
|
||||
.success-icon {
|
||||
width: 48px;
|
||||
height: 48px;
|
||||
border-radius: 50%;
|
||||
background: rgba(78, 205, 196, 0.15);
|
||||
color: #4ecdc4;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
font-size: 1.5rem;
|
||||
font-weight: 700;
|
||||
}
|
||||
|
||||
.success-text {
|
||||
color: #4ecdc4;
|
||||
font-size: 1rem;
|
||||
margin: 0;
|
||||
font-weight: 500;
|
||||
}
|
||||
</style>
|
||||
@@ -272,9 +272,7 @@
|
||||
<style>
|
||||
.transcript-editor {
|
||||
flex: 1;
|
||||
min-width: 0;
|
||||
overflow-y: auto;
|
||||
overflow-x: hidden;
|
||||
padding: 1rem;
|
||||
background: #16213e;
|
||||
border-radius: 8px;
|
||||
@@ -321,7 +319,6 @@
|
||||
.segment-text {
|
||||
line-height: 1.6;
|
||||
padding-left: 0.75rem;
|
||||
white-space: pre-wrap;
|
||||
word-wrap: break-word;
|
||||
overflow-wrap: break-word;
|
||||
}
|
||||
|
||||
@@ -57,12 +57,6 @@
|
||||
isReady = false;
|
||||
});
|
||||
|
||||
wavesurfer.on('error', (err: Error) => {
|
||||
console.error('[voice-to-notes] WaveSurfer error:', err);
|
||||
isLoading = false;
|
||||
loadError = 'Failed to load audio';
|
||||
});
|
||||
|
||||
if (audioUrl) {
|
||||
loadAudio(audioUrl);
|
||||
}
|
||||
|
||||
@@ -10,15 +10,14 @@ export interface AppSettings {
|
||||
litellm_model: string;
|
||||
litellm_api_key: string;
|
||||
litellm_api_base: string;
|
||||
ollama_url: string;
|
||||
ollama_model: string;
|
||||
local_model_path: string;
|
||||
local_binary_path: string;
|
||||
transcription_model: string;
|
||||
transcription_device: string;
|
||||
transcription_language: string;
|
||||
skip_diarization: boolean;
|
||||
hf_token: string;
|
||||
num_speakers: number | null;
|
||||
devtools_enabled: boolean;
|
||||
}
|
||||
|
||||
const defaults: AppSettings = {
|
||||
@@ -30,15 +29,14 @@ const defaults: AppSettings = {
|
||||
litellm_model: 'gpt-4o-mini',
|
||||
litellm_api_key: '',
|
||||
litellm_api_base: '',
|
||||
ollama_url: 'http://localhost:11434',
|
||||
ollama_model: 'llama3.2',
|
||||
local_model_path: '',
|
||||
local_binary_path: 'llama-server',
|
||||
transcription_model: 'base',
|
||||
transcription_device: 'cpu',
|
||||
transcription_language: '',
|
||||
skip_diarization: false,
|
||||
hf_token: '',
|
||||
num_speakers: null,
|
||||
devtools_enabled: false,
|
||||
};
|
||||
|
||||
export const settings = writable<AppSettings>({ ...defaults });
|
||||
@@ -52,27 +50,23 @@ export async function loadSettings(): Promise<void> {
|
||||
}
|
||||
}
|
||||
|
||||
export async function configureAIProvider(s: AppSettings): Promise<void> {
|
||||
export async function saveSettings(s: AppSettings): Promise<void> {
|
||||
settings.set(s);
|
||||
await invoke('save_settings', { settings: s });
|
||||
|
||||
// Configure the AI provider in the Python sidecar
|
||||
const configMap: Record<string, Record<string, string>> = {
|
||||
openai: { api_key: s.openai_api_key, model: s.openai_model },
|
||||
anthropic: { api_key: s.anthropic_api_key, model: s.anthropic_model },
|
||||
litellm: { api_key: s.litellm_api_key, api_base: s.litellm_api_base, model: s.litellm_model },
|
||||
local: { model: s.ollama_model, base_url: s.ollama_url.replace(/\/+$/, '') + '/v1' },
|
||||
local: { model: s.local_model_path, base_url: 'http://localhost:8080' },
|
||||
};
|
||||
const config = configMap[s.ai_provider];
|
||||
if (config) {
|
||||
try {
|
||||
await invoke('ai_configure', { provider: s.ai_provider, config });
|
||||
} catch {
|
||||
// Sidecar may not be running yet
|
||||
// Sidecar may not be running yet — provider will be configured on first use
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export async function saveSettings(s: AppSettings): Promise<void> {
|
||||
settings.set(s);
|
||||
await invoke('save_settings', { settings: s });
|
||||
|
||||
// Configure the AI provider in the Python sidecar
|
||||
await configureAIProvider(s);
|
||||
}
|
||||
|
||||
@@ -8,9 +8,8 @@
|
||||
import AIChatPanel from '$lib/components/AIChatPanel.svelte';
|
||||
import ProgressOverlay from '$lib/components/ProgressOverlay.svelte';
|
||||
import SettingsModal from '$lib/components/SettingsModal.svelte';
|
||||
import SidecarSetup from '$lib/components/SidecarSetup.svelte';
|
||||
import { segments, speakers } from '$lib/stores/transcript';
|
||||
import { settings, loadSettings, configureAIProvider } from '$lib/stores/settings';
|
||||
import { settings, loadSettings } from '$lib/stores/settings';
|
||||
import type { Segment, Speaker } from '$lib/types/transcript';
|
||||
import { onMount, tick } from 'svelte';
|
||||
|
||||
@@ -19,65 +18,13 @@
|
||||
let audioUrl = $state('');
|
||||
let showSettings = $state(false);
|
||||
|
||||
// Sidecar state
|
||||
let sidecarReady = $state(false);
|
||||
let sidecarChecked = $state(false);
|
||||
|
||||
// Sidecar update state
|
||||
let sidecarUpdate = $state<{ current_version: string; latest_version: string } | null>(null);
|
||||
let showUpdateDownload = $state(false);
|
||||
let updateDismissed = $state(false);
|
||||
|
||||
// Project management state
|
||||
let currentProjectPath = $state<string | null>(null);
|
||||
let currentProjectName = $state('');
|
||||
let projectIsV2 = $state(false);
|
||||
let audioFilePath = $state('');
|
||||
let audioWavPath = $state('');
|
||||
|
||||
async function checkSidecar() {
|
||||
try {
|
||||
const ready = await invoke<boolean>('check_sidecar');
|
||||
sidecarReady = ready;
|
||||
} catch {
|
||||
sidecarReady = false;
|
||||
}
|
||||
sidecarChecked = true;
|
||||
}
|
||||
|
||||
async function checkSidecarUpdate() {
|
||||
try {
|
||||
const update = await invoke<{ current_version: string; latest_version: string } | null>('check_sidecar_update');
|
||||
sidecarUpdate = update;
|
||||
} catch {
|
||||
// Silently ignore update check failures
|
||||
}
|
||||
}
|
||||
|
||||
function handleSidecarSetupComplete() {
|
||||
sidecarReady = true;
|
||||
configureAIProvider($settings);
|
||||
checkSidecarUpdate();
|
||||
}
|
||||
|
||||
function handleUpdateComplete() {
|
||||
showUpdateDownload = false;
|
||||
sidecarUpdate = null;
|
||||
}
|
||||
|
||||
onMount(() => {
|
||||
loadSettings().then(() => {
|
||||
// Restore devtools state from settings
|
||||
if ($settings.devtools_enabled) {
|
||||
invoke('toggle_devtools', { open: true });
|
||||
}
|
||||
});
|
||||
checkSidecar().then(() => {
|
||||
if (sidecarReady) {
|
||||
configureAIProvider($settings);
|
||||
checkSidecarUpdate();
|
||||
}
|
||||
});
|
||||
loadSettings();
|
||||
|
||||
// Global keyboard shortcuts
|
||||
function handleKeyDown(e: KeyboardEvent) {
|
||||
@@ -121,32 +68,25 @@
|
||||
};
|
||||
});
|
||||
let isTranscribing = $state(false);
|
||||
let transcriptionCancelled = $state(false);
|
||||
let transcriptionProgress = $state(0);
|
||||
let transcriptionStage = $state('');
|
||||
let transcriptionMessage = $state('');
|
||||
let extractingAudio = $state(false);
|
||||
|
||||
function handleCancelProcessing() {
|
||||
transcriptionCancelled = true;
|
||||
isTranscribing = false;
|
||||
transcriptionProgress = 0;
|
||||
transcriptionStage = '';
|
||||
transcriptionMessage = '';
|
||||
// Clear any partial results
|
||||
segments.set([]);
|
||||
speakers.set([]);
|
||||
}
|
||||
|
||||
// Speaker color palette for auto-assignment
|
||||
const speakerColors = ['#e94560', '#4ecdc4', '#ffe66d', '#a8e6cf', '#ff8b94', '#c7ceea', '#ffd93d', '#6bcb77'];
|
||||
|
||||
function buildProjectData(projectName: string) {
|
||||
return {
|
||||
version: 2,
|
||||
name: projectName,
|
||||
source_file: audioFilePath,
|
||||
audio_wav: 'audio.wav',
|
||||
async function saveProject() {
|
||||
const defaultName = currentProjectName || 'Untitled';
|
||||
const outputPath = await save({
|
||||
defaultPath: `${defaultName}.vtn`,
|
||||
filters: [{ name: 'Voice to Notes Project', extensions: ['vtn'] }],
|
||||
});
|
||||
if (!outputPath) return;
|
||||
|
||||
const projectData = {
|
||||
version: 1,
|
||||
name: outputPath.split(/[\\/]/).pop()?.replace('.vtn', '') || defaultName,
|
||||
audio_file: audioFilePath,
|
||||
created_at: new Date().toISOString(),
|
||||
segments: $segments.map(seg => {
|
||||
const speaker = $speakers.find(s => s.id === seg.speaker_id);
|
||||
@@ -170,75 +110,17 @@
|
||||
color: s.color || '#e94560',
|
||||
})),
|
||||
};
|
||||
}
|
||||
|
||||
/** Save to a specific folder — creates .vtn + audio.wav inside it. */
|
||||
async function saveToFolder(folderPath: string): Promise<boolean> {
|
||||
const projectName = folderPath.split(/[\\/]/).pop() || currentProjectName || 'Untitled';
|
||||
const vtnPath = `${folderPath}/${projectName}.vtn`;
|
||||
const wavPath = `${folderPath}/audio.wav`;
|
||||
const projectData = buildProjectData(projectName);
|
||||
|
||||
try {
|
||||
await invoke('create_dir', { path: folderPath });
|
||||
if (audioWavPath && audioWavPath !== wavPath) {
|
||||
await invoke('copy_file', { src: audioWavPath, dst: wavPath });
|
||||
audioWavPath = wavPath;
|
||||
}
|
||||
await invoke('save_project_file', { path: vtnPath, project: projectData });
|
||||
currentProjectPath = vtnPath;
|
||||
currentProjectName = projectName;
|
||||
projectIsV2 = true;
|
||||
return true;
|
||||
await invoke('save_project_file', { path: outputPath, project: projectData });
|
||||
currentProjectPath = outputPath;
|
||||
currentProjectName = projectData.name;
|
||||
} catch (err) {
|
||||
console.error('Failed to save project:', err);
|
||||
alert(`Failed to save: ${err}`);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
async function saveProject() {
|
||||
// Already saved as v2 folder — save in place
|
||||
if (currentProjectPath && projectIsV2) {
|
||||
const folderPath = currentProjectPath.replace(/[\\/][^\\/]+$/, '');
|
||||
await saveToFolder(folderPath);
|
||||
return;
|
||||
}
|
||||
|
||||
// V1 project opened — migrate to folder structure
|
||||
if (currentProjectPath && !projectIsV2) {
|
||||
const oldVtnDir = currentProjectPath.replace(/[\\/][^\\/]+$/, '');
|
||||
const projectName = currentProjectPath.split(/[\\/]/).pop()?.replace(/\.vtn$/i, '') || 'Untitled';
|
||||
const folderPath = `${oldVtnDir}/${projectName}`;
|
||||
const success = await saveToFolder(folderPath);
|
||||
if (success) {
|
||||
// Optionally remove the old .vtn file
|
||||
try {
|
||||
// Leave old file — user can delete manually
|
||||
} catch {}
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
// Never saved — pick a folder
|
||||
await saveProjectAs();
|
||||
}
|
||||
|
||||
async function saveProjectAs() {
|
||||
// Use save dialog so the user can type a new project name.
|
||||
// The chosen path is treated as the project folder (created if needed).
|
||||
const defaultName = currentProjectName || 'Untitled';
|
||||
const chosenPath = await save({
|
||||
defaultPath: defaultName,
|
||||
title: 'Save Project — enter a project name',
|
||||
});
|
||||
if (!chosenPath) return;
|
||||
|
||||
// Strip any file extension the user may have typed (e.g. ".vtn")
|
||||
const folderPath = chosenPath.replace(/\.[^.\\/]+$/, '');
|
||||
await saveToFolder(folderPath);
|
||||
}
|
||||
|
||||
async function openProject() {
|
||||
const filePath = await open({
|
||||
filters: [{ name: 'Voice to Notes Project', extensions: ['vtn'] }],
|
||||
@@ -248,11 +130,9 @@
|
||||
|
||||
try {
|
||||
const project = await invoke<{
|
||||
version?: number;
|
||||
version: number;
|
||||
name: string;
|
||||
audio_file?: string;
|
||||
source_file?: string;
|
||||
audio_wav?: string;
|
||||
audio_file: string;
|
||||
segments: Array<{
|
||||
text: string;
|
||||
start_ms: number;
|
||||
@@ -302,135 +182,10 @@
|
||||
}));
|
||||
segments.set(newSegments);
|
||||
|
||||
// Determine the directory the .vtn file is in
|
||||
const vtnDir = (filePath as string).replace(/[\\/][^\\/]+$/, '');
|
||||
const version = project.version ?? 1;
|
||||
projectIsV2 = version >= 2;
|
||||
|
||||
// Resolve audio for wavesurfer playback
|
||||
if (version >= 2) {
|
||||
// Version 2: audio_wav is relative to the .vtn directory, source_file is the original import path
|
||||
audioFilePath = project.source_file || '';
|
||||
const wavRelative = project.audio_wav || 'audio.wav';
|
||||
const resolvedWav = `${vtnDir}/${wavRelative}`;
|
||||
|
||||
const wavExists = await invoke<boolean>('check_file_exists', { path: resolvedWav });
|
||||
if (wavExists) {
|
||||
audioWavPath = resolvedWav;
|
||||
audioUrl = convertFileSrc(resolvedWav);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
} else {
|
||||
// WAV missing — try re-extracting from the original source file
|
||||
const sourceExists = audioFilePath ? await invoke<boolean>('check_file_exists', { path: audioFilePath }) : false;
|
||||
if (sourceExists) {
|
||||
extractingAudio = true;
|
||||
await tick();
|
||||
try {
|
||||
const outputPath = `${vtnDir}/${wavRelative}`;
|
||||
const wavPath = await invoke<string>('extract_audio', { filePath: audioFilePath, outputPath });
|
||||
audioWavPath = wavPath;
|
||||
audioUrl = convertFileSrc(wavPath);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
} catch (err) {
|
||||
console.error('Failed to re-extract audio:', err);
|
||||
alert(`Failed to re-extract audio: ${err}`);
|
||||
} finally {
|
||||
extractingAudio = false;
|
||||
}
|
||||
} else {
|
||||
// Both missing — ask user to locate the file
|
||||
const shouldRelink = confirm(
|
||||
'The audio file for this project could not be found.\n\n' +
|
||||
`Original source: ${audioFilePath || '(unknown)'}\n\n` +
|
||||
'Would you like to locate the file?'
|
||||
);
|
||||
if (shouldRelink) {
|
||||
const newPath = await open({
|
||||
multiple: false,
|
||||
filters: [{
|
||||
name: 'Audio/Video',
|
||||
extensions: ['mp3', 'wav', 'flac', 'ogg', 'm4a', 'aac', 'wma',
|
||||
'mp4', 'mkv', 'avi', 'mov', 'webm'],
|
||||
}],
|
||||
});
|
||||
if (newPath) {
|
||||
audioFilePath = newPath;
|
||||
extractingAudio = true;
|
||||
await tick();
|
||||
try {
|
||||
const outputPath = `${vtnDir}/${wavRelative}`;
|
||||
const wavPath = await invoke<string>('extract_audio', { filePath: newPath, outputPath });
|
||||
audioWavPath = wavPath;
|
||||
audioUrl = convertFileSrc(wavPath);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
} catch (err) {
|
||||
console.error('Failed to extract audio from re-linked file:', err);
|
||||
alert(`Failed to extract audio: ${err}`);
|
||||
} finally {
|
||||
extractingAudio = false;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Version 1 (legacy): audio_file is the source path
|
||||
const sourceFile = project.audio_file || '';
|
||||
audioFilePath = sourceFile;
|
||||
|
||||
const sourceExists = sourceFile ? await invoke<boolean>('check_file_exists', { path: sourceFile }) : false;
|
||||
if (sourceExists) {
|
||||
// Extract WAV next to the .vtn file for playback
|
||||
extractingAudio = true;
|
||||
await tick();
|
||||
try {
|
||||
const outputPath = `${vtnDir}/audio.wav`;
|
||||
const wavPath = await invoke<string>('extract_audio', { filePath: sourceFile, outputPath });
|
||||
audioWavPath = wavPath;
|
||||
audioUrl = convertFileSrc(wavPath);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
} catch (err) {
|
||||
console.error('Failed to extract audio:', err);
|
||||
alert(`Failed to extract audio: ${err}`);
|
||||
} finally {
|
||||
extractingAudio = false;
|
||||
}
|
||||
} else {
|
||||
// Source missing — ask user to locate the file
|
||||
const shouldRelink = confirm(
|
||||
'The audio file for this project could not be found.\n\n' +
|
||||
`Original path: ${sourceFile || '(unknown)'}\n\n` +
|
||||
'Would you like to locate the file?'
|
||||
);
|
||||
if (shouldRelink) {
|
||||
const newPath = await open({
|
||||
multiple: false,
|
||||
filters: [{
|
||||
name: 'Audio/Video',
|
||||
extensions: ['mp3', 'wav', 'flac', 'ogg', 'm4a', 'aac', 'wma',
|
||||
'mp4', 'mkv', 'avi', 'mov', 'webm'],
|
||||
}],
|
||||
});
|
||||
if (newPath) {
|
||||
audioFilePath = newPath;
|
||||
extractingAudio = true;
|
||||
await tick();
|
||||
try {
|
||||
const outputPath = `${vtnDir}/audio.wav`;
|
||||
const wavPath = await invoke<string>('extract_audio', { filePath: newPath, outputPath });
|
||||
audioWavPath = wavPath;
|
||||
audioUrl = convertFileSrc(wavPath);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
} catch (err) {
|
||||
console.error('Failed to extract audio from re-linked file:', err);
|
||||
alert(`Failed to extract audio: ${err}`);
|
||||
} finally {
|
||||
extractingAudio = false;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
// Load audio
|
||||
audioFilePath = project.audio_file;
|
||||
audioUrl = convertFileSrc(project.audio_file);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
|
||||
currentProjectPath = filePath as string;
|
||||
currentProjectName = project.name;
|
||||
@@ -461,35 +216,9 @@
|
||||
});
|
||||
if (!filePath) return;
|
||||
|
||||
// Always extract audio to WAV for wavesurfer playback
|
||||
extractingAudio = true;
|
||||
await tick();
|
||||
try {
|
||||
const wavPath = await invoke<string>('extract_audio', { filePath });
|
||||
audioWavPath = wavPath;
|
||||
} catch (err) {
|
||||
console.error('[voice-to-notes] Failed to extract audio:', err);
|
||||
const msg = String(err);
|
||||
if (msg.includes('ffmpeg not found')) {
|
||||
alert(
|
||||
'FFmpeg is required to extract audio.\n\n' +
|
||||
'Install FFmpeg:\n' +
|
||||
' Windows: winget install ffmpeg\n' +
|
||||
' macOS: brew install ffmpeg\n' +
|
||||
' Linux: sudo apt install ffmpeg\n\n' +
|
||||
'Then restart Voice to Notes and try again.'
|
||||
);
|
||||
} else {
|
||||
alert(`Failed to extract audio: ${msg}`);
|
||||
}
|
||||
return;
|
||||
} finally {
|
||||
extractingAudio = false;
|
||||
}
|
||||
|
||||
// Track the original file path for the sidecar (it does its own conversion)
|
||||
// Track the original file path and convert to asset URL for wavesurfer
|
||||
audioFilePath = filePath;
|
||||
audioUrl = convertFileSrc(audioWavPath);
|
||||
audioUrl = convertFileSrc(filePath);
|
||||
waveformPlayer?.loadAudio(audioUrl);
|
||||
|
||||
// Clear previous results
|
||||
@@ -498,7 +227,6 @@
|
||||
|
||||
// Start pipeline (transcription + diarization)
|
||||
isTranscribing = true;
|
||||
transcriptionCancelled = false;
|
||||
transcriptionProgress = 0;
|
||||
transcriptionStage = 'Starting...';
|
||||
transcriptionMessage = 'Initializing pipeline...';
|
||||
@@ -609,9 +337,6 @@
|
||||
numSpeakers: $settings.num_speakers && $settings.num_speakers > 0 ? $settings.num_speakers : undefined,
|
||||
});
|
||||
|
||||
// If cancelled while processing, discard results
|
||||
if (transcriptionCancelled) return;
|
||||
|
||||
// Create speaker entries from pipeline result
|
||||
const newSpeakers: Speaker[] = (result.speakers || []).map((label, idx) => ({
|
||||
id: `speaker-${idx}`,
|
||||
@@ -718,31 +443,14 @@
|
||||
}
|
||||
</script>
|
||||
|
||||
{#if !appReady || !sidecarChecked}
|
||||
{#if !appReady}
|
||||
<div class="splash-screen">
|
||||
<h1 class="splash-title">Voice to Notes</h1>
|
||||
<p class="splash-subtitle">Loading...</p>
|
||||
<div class="splash-spinner"></div>
|
||||
</div>
|
||||
{:else if sidecarChecked && !sidecarReady && !showUpdateDownload}
|
||||
<SidecarSetup onComplete={handleSidecarSetupComplete} />
|
||||
{:else if showUpdateDownload}
|
||||
<SidecarSetup onComplete={handleUpdateComplete} />
|
||||
{:else}
|
||||
<div class="app-shell">
|
||||
{#if sidecarUpdate && !updateDismissed}
|
||||
<div class="update-banner">
|
||||
<span class="update-text">
|
||||
Sidecar update available (v{sidecarUpdate.current_version} → v{sidecarUpdate.latest_version})
|
||||
</span>
|
||||
<button class="update-btn" onclick={() => showUpdateDownload = true}>
|
||||
Update
|
||||
</button>
|
||||
<button class="update-dismiss" onclick={() => updateDismissed = true} title="Dismiss">
|
||||
×
|
||||
</button>
|
||||
</div>
|
||||
{/if}
|
||||
<div class="app-header">
|
||||
<div class="header-actions">
|
||||
<button class="settings-btn" onclick={openProject} disabled={isTranscribing}>
|
||||
@@ -750,10 +458,7 @@
|
||||
</button>
|
||||
{#if $segments.length > 0}
|
||||
<button class="settings-btn" onclick={saveProject}>
|
||||
Save
|
||||
</button>
|
||||
<button class="settings-btn" onclick={saveProjectAs}>
|
||||
Save As
|
||||
Save Project
|
||||
</button>
|
||||
{/if}
|
||||
<button class="import-btn" onclick={handleFileImport} disabled={isTranscribing}>
|
||||
@@ -802,18 +507,8 @@
|
||||
percent={transcriptionProgress}
|
||||
stage={transcriptionStage}
|
||||
message={transcriptionMessage}
|
||||
onCancel={handleCancelProcessing}
|
||||
/>
|
||||
|
||||
{#if extractingAudio}
|
||||
<div class="extraction-overlay">
|
||||
<div class="extraction-card">
|
||||
<div class="extraction-spinner"></div>
|
||||
<p>Extracting audio...</p>
|
||||
</div>
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
<SettingsModal
|
||||
visible={showSettings}
|
||||
onClose={() => showSettings = false}
|
||||
@@ -979,80 +674,4 @@
|
||||
@keyframes spin {
|
||||
to { transform: rotate(360deg); }
|
||||
}
|
||||
|
||||
/* Sidecar update banner */
|
||||
.update-banner {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.75rem;
|
||||
padding: 0.5rem 1rem;
|
||||
background: rgba(78, 205, 196, 0.1);
|
||||
border-bottom: 1px solid rgba(78, 205, 196, 0.25);
|
||||
color: #e0e0e0;
|
||||
font-size: 0.85rem;
|
||||
}
|
||||
.update-text {
|
||||
flex: 1;
|
||||
color: #b0b0b0;
|
||||
}
|
||||
.update-btn {
|
||||
background: #4ecdc4;
|
||||
border: none;
|
||||
color: #0a0a23;
|
||||
padding: 0.3rem 0.85rem;
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
font-size: 0.8rem;
|
||||
font-weight: 600;
|
||||
}
|
||||
.update-btn:hover {
|
||||
background: #3dbdb5;
|
||||
}
|
||||
.update-dismiss {
|
||||
background: none;
|
||||
border: none;
|
||||
color: #888;
|
||||
font-size: 1.1rem;
|
||||
cursor: pointer;
|
||||
padding: 0.1rem 0.3rem;
|
||||
line-height: 1;
|
||||
}
|
||||
.update-dismiss:hover {
|
||||
color: #e0e0e0;
|
||||
}
|
||||
|
||||
/* Audio extraction overlay */
|
||||
.extraction-overlay {
|
||||
position: fixed;
|
||||
inset: 0;
|
||||
background: rgba(0, 0, 0, 0.8);
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
z-index: 9999;
|
||||
}
|
||||
.extraction-card {
|
||||
background: #16213e;
|
||||
padding: 2rem 2.5rem;
|
||||
border-radius: 12px;
|
||||
color: #e0e0e0;
|
||||
border: 1px solid #2a3a5e;
|
||||
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
gap: 1rem;
|
||||
}
|
||||
.extraction-card p {
|
||||
margin: 0;
|
||||
font-size: 1rem;
|
||||
}
|
||||
.extraction-spinner {
|
||||
width: 32px;
|
||||
height: 32px;
|
||||
border: 3px solid #2a3a5e;
|
||||
border-top-color: #e94560;
|
||||
border-radius: 50%;
|
||||
animation: spin 0.8s linear infinite;
|
||||
}
|
||||
</style>
|
||||
|
||||
Reference in New Issue
Block a user