chore: bump version to 2.0.14 [skip ci]

The default remote.mode changed from 'local' to 'byok', causing
the apply_settings test to detect a mode mismatch and trigger an
unexpected engine reload. Pin remote.mode to 'local' in the test
to match the controller's assumed current mode.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.gitea/workflows/build-sidecar-linux.yml

@@ -41,10 +41,11 @@ jobs:
           sudo apt-get install -y portaudio19-dev
 
       - name: Build sidecar (CPU)
-        env:
-          UV_NO_SOURCES: "1"
         run: |
-          uv sync
+          uv sync --no-sources
+          # PyPI's default torch on Linux includes CUDA (~800MB).
+          # Replace with CPU-only torch from the dedicated index.
+          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
           .venv/bin/pyinstaller local-transcription-headless.spec
 
       - name: Package sidecar (CPU)

.gitea/workflows/build-sidecar-windows.yml

@@ -56,10 +56,11 @@ jobs:
 
       - name: Build sidecar (CPU)
         shell: powershell
-        env:
-          UV_NO_SOURCES: "1"
         run: |
+          $env:UV_NO_SOURCES = "1"
           uv sync
+          # PyPI's default torch includes CUDA. Replace with CPU-only.
+          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
           .venv\Scripts\pyinstaller.exe local-transcription-headless.spec
 
       - name: Package sidecar (CPU)

.gitea/workflows/cleanup-releases.yml

@@ -0,0 +1,102 @@
+name: Cleanup Old Releases
+
+on:
+  workflow_dispatch:
+    inputs:
+      keep_app_releases:
+        description: 'Number of app releases to keep'
+        required: false
+        default: '3'
+      keep_sidecar_releases:
+        description: 'Number of sidecar releases to keep'
+        required: false
+        default: '2'
+      dry_run:
+        description: 'Dry run (show what would be deleted without deleting)'
+        required: false
+        default: 'true'
+
+jobs:
+  cleanup:
+    name: Cleanup Old Releases
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cleanup releases
+        env:
+          BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
+        run: |
+          REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          KEEP_APP="${{ inputs.keep_app_releases }}"
+          KEEP_SIDECAR="${{ inputs.keep_sidecar_releases }}"
+          DRY_RUN="${{ inputs.dry_run }}"
+
+          echo "=== Cleanup Configuration ==="
+          echo "Keep app releases: ${KEEP_APP}"
+          echo "Keep sidecar releases: ${KEEP_SIDECAR}"
+          echo "Dry run: ${DRY_RUN}"
+          echo ""
+
+          # Fetch all releases
+          ALL_RELEASES=$(curl -s -H "Authorization: token ${BUILD_TOKEN}" \
+            "${REPO_API}/releases?limit=50")
+
+          # ── App releases (v* tags, not sidecar-v*) ──
+          echo "=== App Releases ==="
+          APP_RELEASES=$(echo "$ALL_RELEASES" | jq -c '[.[] | select(.tag_name | startswith("v")) | select(.tag_name | startswith("sidecar") | not)]')
+          APP_TOTAL=$(echo "$APP_RELEASES" | jq 'length')
+          echo "Found ${APP_TOTAL} app releases, keeping ${KEEP_APP}"
+
+          if [ "$APP_TOTAL" -gt "$KEEP_APP" ]; then
+            echo "$APP_RELEASES" | jq -c ".[$KEEP_APP:][]" | while read -r release; do
+              ID=$(echo "$release" | jq -r '.id')
+              TAG=$(echo "$release" | jq -r '.tag_name')
+              SIZE=$(echo "$release" | jq '[.assets[]?.size // 0] | add // 0')
+              SIZE_MB=$(echo "scale=1; $SIZE / 1048576" | bc 2>/dev/null || echo "?")
+
+              # Protect v1.4.0 (last pre-Tauri release)
+              if [ "$TAG" = "v1.4.0" ]; then
+                echo "  PROTECT ${TAG} (${SIZE_MB} MB)"
+                continue
+              fi
+
+              if [ "$DRY_RUN" = "true" ]; then
+                echo "  WOULD DELETE ${TAG} (ID: ${ID}, ${SIZE_MB} MB)"
+              else
+                echo "  DELETING ${TAG} (ID: ${ID}, ${SIZE_MB} MB)..."
+                curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                  "${REPO_API}/releases/${ID}"
+              fi
+            done
+          else
+            echo "  Nothing to clean up"
+          fi
+
+          echo ""
+
+          # ── Sidecar releases (sidecar-v* tags) ──
+          echo "=== Sidecar Releases ==="
+          SIDECAR_RELEASES=$(echo "$ALL_RELEASES" | jq -c '[.[] | select(.tag_name | startswith("sidecar-v"))]')
+          SIDECAR_TOTAL=$(echo "$SIDECAR_RELEASES" | jq 'length')
+          echo "Found ${SIDECAR_TOTAL} sidecar releases, keeping ${KEEP_SIDECAR}"
+
+          if [ "$SIDECAR_TOTAL" -gt "$KEEP_SIDECAR" ]; then
+            echo "$SIDECAR_RELEASES" | jq -c ".[$KEEP_SIDECAR:][]" | while read -r release; do
+              ID=$(echo "$release" | jq -r '.id')
+              TAG=$(echo "$release" | jq -r '.tag_name')
+              SIZE=$(echo "$release" | jq '[.assets[]?.size // 0] | add // 0')
+              SIZE_MB=$(echo "scale=1; $SIZE / 1048576" | bc 2>/dev/null || echo "?")
+
+              if [ "$DRY_RUN" = "true" ]; then
+                echo "  WOULD DELETE ${TAG} (ID: ${ID}, ${SIZE_MB} MB)"
+              else
+                echo "  DELETING ${TAG} (ID: ${ID}, ${SIZE_MB} MB)..."
+                curl -s -X DELETE -H "Authorization: token ${BUILD_TOKEN}" \
+                  "${REPO_API}/releases/${ID}"
+              fi
+            done
+          else
+            echo "  Nothing to clean up"
+          fi
+
+          echo ""
+          echo "=== Done ==="

.gitea/workflows/release.yml

@@ -36,9 +36,6 @@ jobs:
     name: Bump version and tag
     needs: test
     runs-on: ubuntu-latest
-    outputs:
-      new_version: ${{ steps.bump.outputs.new_version }}
-      tag: ${{ steps.bump.outputs.tag }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -50,7 +47,6 @@ jobs:
           git config user.email "actions@gitea.local"
 
       - name: Bump patch version
-        id: bump
         run: |
           CURRENT=$(grep '"version"' package.json | head -1 | sed 's/.*"version": *"\([^"]*\)".*/\1/')
           echo "Current version: ${CURRENT}"
@@ -68,35 +64,34 @@ jobs:
           sed -i "s/__version__ = \"${CURRENT}\"/__version__ = \"${NEW_VERSION}\"/" version.py
           sed -i "s/__version_info__ = .*/__version_info__ = (${MAJOR}, ${MINOR}, ${NEW_PATCH})/" version.py
 
-          echo "new_version=${NEW_VERSION}" >> $GITHUB_OUTPUT
-          echo "tag=v${NEW_VERSION}" >> $GITHUB_OUTPUT
+          # Write to env file instead of step outputs (avoids act runner bug)
+          echo "NEW_VERSION=${NEW_VERSION}" >> $GITHUB_ENV
+          echo "RELEASE_TAG=v${NEW_VERSION}" >> $GITHUB_ENV
 
       - 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 version.py
           git commit -m "chore: bump version to ${NEW_VERSION} [skip ci]"
-          git tag "v${NEW_VERSION}"
+          git tag "${RELEASE_TAG}"
 
           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}"
+          git push "${REMOTE_URL}" "${RELEASE_TAG}"
 
       - 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="Local Transcription ${TAG}"
+          RELEASE_NAME="Local Transcription ${RELEASE_TAG}"
 
           curl -s -X POST \
             -H "Authorization: token ${BUILD_TOKEN}" \
             -H "Content-Type: application/json" \
-            -d "{\"tag_name\": \"${TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated build.\", \"draft\": false, \"prerelease\": false}" \
+            -d "{\"tag_name\": \"${RELEASE_TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated build.\", \"draft\": false, \"prerelease\": false}" \
             "${REPO_API}/releases"
           echo "Created release: ${RELEASE_NAME}"
 
@@ -105,18 +100,14 @@ jobs:
           BUILD_TOKEN: ${{ secrets.BUILD_TOKEN }}
         run: |
           REPO_API="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
-          TAG="${{ steps.bump.outputs.tag }}"
 
           for workflow in build-app-linux.yml build-app-windows.yml build-app-macos.yml; do
-            echo "Dispatching ${workflow} for ${TAG}..."
+            echo "Dispatching ${workflow} for ${RELEASE_TAG}..."
             HTTP_CODE=$(curl -s -w "%{http_code}" -o /tmp/dispatch_resp.txt -X POST \
               -H "Authorization: token ${BUILD_TOKEN}" \
               -H "Content-Type: application/json" \
-              -d "{\"ref\": \"main\", \"inputs\": {\"tag\": \"${TAG}\"}}" \
+              -d "{\"ref\": \"main\", \"inputs\": {\"tag\": \"${RELEASE_TAG}\"}}" \
               "${REPO_API}/actions/workflows/${workflow}/dispatches")
             echo "  -> HTTP ${HTTP_CODE}"
-            [ "$HTTP_CODE" != "204" ] && cat /tmp/dispatch_resp.txt && echo ""
+            if [ "$HTTP_CODE" != "204" ]; then cat /tmp/dispatch_resp.txt; echo ""; fi
           done
-
-      # NOTE: Automatic cleanup disabled -- it races with async builds.
-      # Clean up old releases manually from the Gitea UI when needed.

.gitea/workflows/sidecar-release.yml

@@ -27,40 +27,17 @@ jobs:
     needs: test
     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 backend changes
-        id: check_changes
-        run: |
-          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            exit 0
-          fi
-          CHANGED=$(git diff --name-only HEAD~1 HEAD -- client/ server/ backend/ pyproject.toml local-transcription-headless.spec 2>/dev/null || echo "")
-          if [ -n "$CHANGED" ]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-            echo "Backend changes detected: $CHANGED"
-          else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-            echo "No backend 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: |
           CURRENT=$(grep '^version = ' pyproject.toml | head -1 | sed 's/version = "\(.*\)"/\1/')
           echo "Current sidecar version: ${CURRENT}"
@@ -74,56 +51,49 @@ jobs:
 
           sed -i "s/^version = \"${CURRENT}\"/version = \"${NEW_VERSION}\"/" pyproject.toml
 
-          echo "version=${NEW_VERSION}" >> $GITHUB_OUTPUT
-          echo "tag=sidecar-v${NEW_VERSION}" >> $GITHUB_OUTPUT
+          # Write to env file instead of step outputs (avoids act runner bug)
+          echo "NEW_VERSION=${NEW_VERSION}" >> $GITHUB_ENV
+          echo "RELEASE_TAG=sidecar-v${NEW_VERSION}" >> $GITHUB_ENV
 
       - 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 pyproject.toml
           git commit -m "chore: bump sidecar version to ${NEW_VERSION} [skip ci]"
-          git tag "${TAG}"
+          git tag "${RELEASE_TAG}"
 
           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}"
+          git push "${REMOTE_URL}" "${RELEASE_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}"
+          RELEASE_NAME="Sidecar v${NEW_VERSION}"
 
           curl -s -X POST \
             -H "Authorization: token ${BUILD_TOKEN}" \
             -H "Content-Type: application/json" \
-            -d "{\"tag_name\": \"${TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated sidecar build.\", \"draft\": false, \"prerelease\": false}" \
+            -d "{\"tag_name\": \"${RELEASE_TAG}\", \"name\": \"${RELEASE_NAME}\", \"body\": \"Automated sidecar build.\", \"draft\": false, \"prerelease\": false}" \
             "${REPO_API}/releases"
           echo "Created release: ${RELEASE_NAME}"
 
       - name: Trigger per-OS sidecar builds
-        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 }}"
 
           for workflow in build-sidecar-linux.yml build-sidecar-windows.yml build-sidecar-macos.yml build-sidecar-cloud.yml; do
-            echo "Dispatching ${workflow} for ${TAG}..."
+            echo "Dispatching ${workflow} for ${RELEASE_TAG}..."
             HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST \
               -H "Authorization: token ${BUILD_TOKEN}" \
               -H "Content-Type: application/json" \
-              -d "{\"ref\": \"main\", \"inputs\": {\"tag\": \"${TAG}\"}}" \
+              -d "{\"ref\": \"main\", \"inputs\": {\"tag\": \"${RELEASE_TAG}\"}}" \
               "${REPO_API}/actions/workflows/${workflow}/dispatches")
             echo "  -> HTTP ${HTTP_CODE}"
           done

README.md

@@ -267,6 +267,15 @@ Both workflows require a `BUILD_TOKEN` secret in the repo settings (Gitea API to
 
 ## Troubleshooting
 
+### macOS: "App is damaged and can't be opened"
+macOS Gatekeeper blocks unsigned applications. Since the app is not yet signed with an Apple Developer certificate, you need to remove the quarantine flag before opening:
+
+```bash
+xattr -cr "/Applications/Local Transcription.app"
+```
+
+Then open the app normally. You only need to do this once after downloading.
+
 ### Model Loading Issues
 - Models download automatically on first use to `~/.cache/huggingface/`
 - First run requires internet connection

backend/api_server.py

@@ -151,14 +151,24 @@ class APIServer:
 
         @app.post("/api/start")
         async def start_transcription():
-            success, message = ctrl.start_transcription()
+            import asyncio
+            # Run in thread pool to avoid blocking the event loop
+            # (start_recording can block up to 15s waiting for Deepgram WS)
+            loop = asyncio.get_event_loop()
+            success, message = await loop.run_in_executor(
+                None, ctrl.start_transcription
+            )
             if not success:
                 raise HTTPException(status_code=400, detail=message)
             return {"status": "ok", "message": message}
 
         @app.post("/api/stop")
         async def stop_transcription():
-            success, message = ctrl.stop_transcription()
+            import asyncio
+            loop = asyncio.get_event_loop()
+            success, message = await loop.run_in_executor(
+                None, ctrl.stop_transcription
+            )
             if not success:
                 raise HTTPException(status_code=400, detail=message)
             return {"status": "ok", "message": message}
@@ -223,7 +233,11 @@ class APIServer:
 
         @app.post("/api/reload-engine")
         async def reload_engine():
-            success, message = ctrl.reload_engine()
+            import asyncio
+            loop = asyncio.get_event_loop()
+            success, message = await loop.run_in_executor(
+                None, ctrl.reload_engine
+            )
             if not success:
                 raise HTTPException(status_code=500, detail=message)
             return {"status": "ok", "message": message}

backend/app_controller.py

@@ -396,7 +396,14 @@ class AppController:
         try:
             success = self.transcription_engine.start_recording()
             if not success:
-                return False, "Failed to start recording"
+                import logging
+                # Check if there's a recent error in the logger
+                err_detail = getattr(self.transcription_engine, '_last_error', '')
+                msg = f"Failed to start recording"
+                if err_detail:
+                    msg += f": {err_detail}"
+                print(f"ERROR: {msg}")
+                return False, msg
 
             # Start server sync if enabled
             if self.config.get('server_sync.enabled', False):

backend/tests/test_app_controller.py

@@ -125,6 +125,8 @@ def test_apply_settings_no_reload_when_same(controller):
     # Ensure config returns the same values
     controller.config.set("transcription.model", "base.en")
     controller.config.set("transcription.device", "auto")
+    # Remote mode must also match (no engine means current mode is 'local')
+    controller.config.set("remote.mode", "local")
 
     controller.reload_engine = MagicMock(return_value=(True, "reloaded"))
 

client/deepgram_transcription.py

@@ -156,17 +156,30 @@ class DeepgramTranscriptionEngine:
             return True
 
         self._stop_event.clear()
+        self._ws_connected = threading.Event()
         self._is_recording = True
 
         # Start the asyncio event-loop thread (handles WS send/receive)
         self._thread = threading.Thread(target=self._run_event_loop, daemon=True)
         self._thread.start()
 
+        # Wait for the WebSocket to connect before starting audio capture.
+        # Without this, audio chunks arrive before the WS is open -> broken pipe.
+        if not self._ws_connected.wait(timeout=15):
+            logger.error("Timed out waiting for Deepgram WebSocket connection")
+            print("ERROR: Timed out waiting for Deepgram WebSocket connection")
+            self._last_error = "Timed out connecting to Deepgram"
+            self._is_recording = False
+            self._stop_event.set()
+            return False
+
         # Start the audio capture stream
         try:
             self._start_audio_stream()
         except Exception as exc:
             logger.error("Failed to open audio stream: %s", exc)
+            print(f"ERROR: Failed to open audio stream: {exc}")
+            self._last_error = f"Audio stream error: {exc}"
             self._is_recording = False
             self._stop_event.set()
             return False
@@ -283,6 +296,11 @@ class DeepgramTranscriptionEngine:
                 if not await self._managed_handshake():
                     return
 
+            # Signal that the WebSocket is connected and ready
+            logger.info("WebSocket connected to Deepgram")
+            if hasattr(self, '_ws_connected'):
+                self._ws_connected.set()
+
             # Run send and receive concurrently
             await asyncio.gather(
                 self._send_loop(),

config/default_config.yaml

@@ -42,7 +42,7 @@ transcription:
 
 server_sync:
   enabled: false
-  url: "http://localhost:3000/api/send"
+  url: ""
   room: "default"
   passphrase: ""
   # Font settings are now in the display section (shared for local and server sync)
@@ -69,7 +69,7 @@ web_server:
   host: "127.0.0.1"
 
 remote:
-  mode: local  # local | managed | byok
+  mode: byok  # local | managed | byok
   server_url: ""  # Proxy server URL for managed mode (e.g., wss://your-proxy.com)
   auth_token: ""  # JWT stored after login (managed mode)
   byok_api_key: ""  # Deepgram API key for BYOK mode

local-transcription-cloud.spec

@@ -19,9 +19,26 @@ datas = [
     ('config/default_config.yaml', 'config'),
 ]
 
+# Collect sounddevice's bundled PortAudio library (_sounddevice_data)
+try:
+    import sounddevice
+    sd_path = os.path.dirname(sounddevice.__file__)
+    sd_data = os.path.join(sd_path, '_sounddevice_data')
+    if os.path.exists(sd_data):
+        datas.append((sd_data, '_sounddevice_data'))
+        print(f"  + Collected sounddevice PortAudio data from {sd_data}")
+    # Also collect the package itself
+    sd_datas = collect_data_files('sounddevice')
+    if sd_datas:
+        datas += sd_datas
+        print(f"  + Collected {len(sd_datas)} sounddevice data files")
+except ImportError:
+    print("  - Warning: sounddevice not found")
+
 # Hidden imports -- only lightweight deps needed for Deepgram streaming
 hiddenimports = [
     'sounddevice',
+    '_sounddevice_data',
     'numpy',
     # FastAPI and dependencies
     'fastapi',

local-transcription-headless.spec

@@ -38,6 +38,21 @@ datas = [
     (vad_assets_path, 'faster_whisper/assets'),
 ] + pvporcupine_data_files
 
+# Collect sounddevice's bundled PortAudio library (_sounddevice_data)
+try:
+    import sounddevice
+    sd_path = os.path.dirname(sounddevice.__file__)
+    sd_data = os.path.join(sd_path, '_sounddevice_data')
+    if os.path.exists(sd_data):
+        datas.append((sd_data, '_sounddevice_data'))
+        print(f"  + Collected sounddevice PortAudio data from {sd_data}")
+    sd_datas = collect_data_files('sounddevice')
+    if sd_datas:
+        datas += sd_datas
+        print(f"  + Collected {len(sd_datas)} sounddevice data files")
+except ImportError:
+    print("  - Warning: sounddevice not found")
+
 # Hidden imports -- NO PySide6/Qt needed for headless backend
 hiddenimports = [
     # Transcription engine
@@ -46,6 +61,7 @@ hiddenimports = [
     'faster_whisper.vad',
     'ctranslate2',
     'sounddevice',
+    '_sounddevice_data',
     'scipy',
     'scipy.signal',
     'numpy',

package.json

@@ -1,7 +1,7 @@
 {
   "name": "local-transcription",
   "private": true,
-  "version": "2.0.8",
+  "version": "2.0.14",
   "type": "module",
   "scripts": {
     "dev": "vite dev",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "local-transcription"
-version = "1.0.6"
+version = "1.0.11"
 description = "A standalone desktop application for real-time speech-to-text transcription using Whisper models"
 readme = "README.md"
 requires-python = ">=3.9"

server/nodejs/server.js

@@ -703,6 +703,36 @@ app.post('/api/send', async (req, res) => {
     }
 });
 
+// Create room explicitly (no transcription needed)
+app.post('/api/create-room', async (req, res) => {
+    try {
+        const { room, passphrase } = req.body;
+
+        if (!room || !passphrase) {
+            return res.status(400).json({ error: 'Missing room or passphrase' });
+        }
+
+        // Check if room already exists
+        const existing = await loadRoom(room);
+        if (existing) {
+            const valid = await verifyPassphrase(room, passphrase);
+            if (!valid) {
+                return res.status(401).json({ error: 'Room exists with different passphrase' });
+            }
+            return res.json({ status: 'ok', room, created: false, message: 'Room already exists' });
+        }
+
+        // Create the room (verifyPassphrase creates it if it doesn't exist)
+        await verifyPassphrase(room, passphrase);
+
+        console.log(`[Room] Created room "${room}"`);
+        res.json({ status: 'ok', room, created: true });
+    } catch (err) {
+        console.error('Error in /api/create-room:', err);
+        res.status(500).json({ error: err.message });
+    }
+});
+
 // List transcriptions
 app.get('/api/list', async (req, res) => {
     try {

src-tauri/Cargo.lock

@@ -1881,7 +1881,7 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
 
 [[package]]
 name = "local-transcription"
-version = "2.0.3"
+version = "2.0.12"
 dependencies = [
  "bytes",
  "chrono",

src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "local-transcription"
-version = "2.0.8"
+version = "2.0.14"
 description = "Real-time speech-to-text transcription for streamers"
 authors = ["Local Transcription Contributors"]
 edition = "2021"

src-tauri/src/lib.rs

@@ -71,6 +71,28 @@ pub fn run() {
             sidecar::reset_sidecar,
             write_log,
         ])
-        .run(tauri::generate_context!())
-        .expect("error while running tauri application");
+        .build(tauri::generate_context!())
+        .expect("error while building tauri application")
+        .run(|app, event| {
+            match event {
+                tauri::RunEvent::Exit => {
+                    if let Some(state) = app.try_state::<sidecar::ManagedSidecar>() {
+                        if let Ok(mut mgr) = state.0.lock() {
+                            eprintln!("[app] Stopping sidecar on exit...");
+                            mgr.stop();
+                        }
+                    }
+                }
+                tauri::RunEvent::ExitRequested { .. } => {
+                    // Also stop sidecar on exit request (Cmd+Q on macOS)
+                    if let Some(state) = app.try_state::<sidecar::ManagedSidecar>() {
+                        if let Ok(mut mgr) = state.0.lock() {
+                            eprintln!("[app] Stopping sidecar on exit request...");
+                            mgr.stop();
+                        }
+                    }
+                }
+                _ => {}
+            }
+        });
 }

src-tauri/tauri.conf.json

@@ -1,6 +1,6 @@
 {
   "productName": "Local Transcription",
-  "version": "2.0.8",
+  "version": "2.0.14",
   "identifier": "net.anhonesthost.local-transcription",
   "build": {
     "frontendDist": "../dist",

src/App.svelte

@@ -15,6 +15,7 @@
   let sidecarState = $state<SidecarState>("checking");
   let debugLog = $state("");
   let availableUpdate = $state("");
+  let appVersion = $state("");
 
   let obsDisplayUrl = $derived(backendStore.obsUrl);
   let syncDisplayUrl = $derived(backendStore.syncUrl);
@@ -108,6 +109,14 @@
   }
 
   onMount(() => {
+    // Get app version from Tauri
+    import("@tauri-apps/api/app").then(({ getVersion }) =>
+      getVersion().then((v) => { appVersion = v; })
+    ).catch(() => {
+      // Browser dev mode -- read from package.json or use fallback
+      appVersion = "dev";
+    });
+
     checkAndLaunchSidecar();
 
     return () => {
@@ -201,7 +210,7 @@
     <TranscriptionDisplay />
     <Controls />
 
-    <div class="version-label">v{backendStore.version}</div>
+    <div class="version-label">v{appVersion || backendStore.version}</div>
   </div>
 
   {#if showSettings}

src/lib/components/Controls.svelte

@@ -1,5 +1,6 @@
 <script lang="ts">
   import { backendStore } from "$lib/stores/backend";
+  import { configStore } from "$lib/stores/config";
   import { transcriptionStore } from "$lib/stores/transcriptions";
 
   let isTranscribing = $derived(backendStore.appState === "transcribing");
@@ -8,21 +9,39 @@
   );
   let isLoading = $state(false);
 
+  let remoteMode = $derived(configStore.config.remote.mode);
+  let byokApiKey = $derived(configStore.config.remote.byok_api_key);
+  let authToken = $derived(configStore.config.remote.auth_token);
+
+  let cloudConfigured = $derived(
+    remoteMode === "local" ||
+    (remoteMode === "byok" && byokApiKey.trim() !== "") ||
+    (remoteMode === "managed" && authToken.trim() !== "")
+  );
+
+  let errorMessage = $state("");
+
   async function toggleTranscription() {
     if (isLoading) return;
     isLoading = true;
+    errorMessage = "";
     try {
       if (isTranscribing) {
         await backendStore.apiPost("/api/stop");
       } else {
         await backendStore.apiPost("/api/start");
       }
-      // Poll status to update UI immediately instead of waiting
-      // for WebSocket broadcast (which can be delayed or missed)
-      await backendStore.pollStatus();
-    } catch (err) {
-      console.error("Failed to toggle transcription:", err);
+    } catch (err: unknown) {
+      const msg = err instanceof Error ? err.message : String(err);
+      // Ignore "Already transcribing/not transcribing" -- just sync the state
+      if (!msg.includes("400")) {
+        console.error("Failed to toggle transcription:", msg);
+        errorMessage = msg;
+      }
     } finally {
+      // Always poll status to sync UI with actual backend state,
+      // even if the API call failed (e.g. "Already transcribing")
+      await backendStore.pollStatus();
       isLoading = false;
     }
   }
@@ -86,7 +105,7 @@
   <button
     class={isTranscribing ? "danger" : "primary"}
     onclick={toggleTranscription}
-    disabled={!isReady || isLoading}
+    disabled={!isReady || isLoading || !cloudConfigured}
   >
     {#if isLoading}
       ...
@@ -104,9 +123,43 @@
   <button onclick={saveTranscriptions} disabled={!backendStore.connected}>
     Save
   </button>
+
+  {#if errorMessage}
+    <span class="error-msg">{errorMessage}</span>
+  {/if}
+
+  {#if !cloudConfigured && isReady}
+    <div class="cloud-warning">
+      {#if remoteMode === "byok"}
+        <span>API key required. Get one at
+          <a href="https://console.deepgram.com" target="_blank" rel="noopener">console.deepgram.com</a>,
+          then enter it in Settings.</span>
+      {:else if remoteMode === "managed"}
+        <span>Login required. Open Settings to log in.</span>
+      {/if}
+    </div>
+  {/if}
 </div>
 
 <style>
+  .error-msg {
+    color: #f44336;
+    font-size: 12px;
+    margin-left: 8px;
+  }
+
+  .cloud-warning {
+    font-size: 12px;
+    color: #ff9800;
+    margin-left: 8px;
+    flex: 1;
+  }
+
+  .cloud-warning a {
+    color: #4fc3f7;
+    text-decoration: underline;
+  }
+
   .controls {
     display: flex;
     align-items: center;

src/lib/components/Settings.svelte

@@ -46,6 +46,14 @@
   let managedPassword = $state("");
   let autoCheckUpdates = $state(true);
 
+  let isCloudMode = $derived(remoteMode === "managed" || remoteMode === "byok");
+
+  // Room creation / join state
+  let shareCode = $state("");
+  let joinCode = $state("");
+  let roomCreating = $state(false);
+  let roomCreateMessage = $state("");
+
   let saving = $state(false);
   let saveMessage = $state("");
 
@@ -266,6 +274,99 @@
     }
   }
 
+  const CAPTION_SERVER = "https://caption.shadowdao.com";
+
+  function generateRandomName(): string {
+    const adjectives = ['swift', 'bright', 'cosmic', 'electric', 'turbo', 'mega', 'ultra', 'super', 'hyper', 'alpha'];
+    const nouns = ['phoenix', 'dragon', 'tiger', 'falcon', 'comet', 'storm', 'blaze', 'thunder', 'frost', 'nebula'];
+    const num = Math.floor(Math.random() * 10000);
+    return `${adjectives[Math.floor(Math.random() * adjectives.length)]}-${nouns[Math.floor(Math.random() * nouns.length)]}-${num}`;
+  }
+
+  function generateRandomPassphrase(): string {
+    const chars = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789';
+    let result = '';
+    for (let i = 0; i < 16; i++) {
+      result += chars.charAt(Math.floor(Math.random() * chars.length));
+    }
+    return result;
+  }
+
+  function encodeShareCode(url: string, room: string, passphrase: string): string {
+    return btoa(JSON.stringify({ url, room, passphrase }));
+  }
+
+  function decodeShareCode(code: string): { url: string; room: string; passphrase: string } | null {
+    try {
+      const json = JSON.parse(atob(code.trim()));
+      if (json.url && json.room && json.passphrase) {
+        return json;
+      }
+      return null;
+    } catch {
+      return null;
+    }
+  }
+
+  async function handleCreateRoom() {
+    roomCreating = true;
+    roomCreateMessage = "";
+    shareCode = "";
+
+    const room = generateRandomName();
+    const passphrase = generateRandomPassphrase();
+    const serverSendUrl = `${CAPTION_SERVER}/api/send`;
+
+    try {
+      const resp = await fetch(`${CAPTION_SERVER}/api/create-room`, {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ room, passphrase }),
+      });
+
+      if (!resp.ok) {
+        const err = await resp.json().catch(() => ({ error: "Request failed" }));
+        roomCreateMessage = `Error: ${err.error || resp.statusText}`;
+        return;
+      }
+
+      syncUrl = serverSendUrl;
+      syncRoom = room;
+      syncPassphrase = passphrase;
+      syncEnabled = true;
+
+      shareCode = encodeShareCode(serverSendUrl, room, passphrase);
+      roomCreateMessage = "Room created! Share the code below with others.";
+    } catch (err) {
+      roomCreateMessage = `Error: ${err instanceof Error ? err.message : String(err)}`;
+    } finally {
+      roomCreating = false;
+    }
+  }
+
+  function handleJoinRoom() {
+    const decoded = decodeShareCode(joinCode);
+    if (!decoded) {
+      roomCreateMessage = "Invalid share code. Please check and try again.";
+      return;
+    }
+    syncUrl = decoded.url;
+    syncRoom = decoded.room;
+    syncPassphrase = decoded.passphrase;
+    syncEnabled = true;
+    joinCode = "";
+    roomCreateMessage = "Room joined! Fields have been auto-filled.";
+  }
+
+  async function copyShareCode() {
+    try {
+      await navigator.clipboard.writeText(shareCode);
+      roomCreateMessage = "Share code copied to clipboard!";
+    } catch {
+      roomCreateMessage = "Failed to copy. Please select and copy manually.";
+    }
+  }
+
   function handleOverlayClick(e: MouseEvent) {
     if ((e.target as HTMLElement).classList.contains("settings-overlay")) {
       handleCancel();
@@ -327,7 +428,90 @@
         </div>
       </section>
 
-      <!-- Transcription Settings -->
+      <!-- Remote Transcription (moved up for cloud-first UX) -->
+      <section class="settings-section">
+        <h3>Transcription Mode</h3>
+        <div class="radio-group">
+          <label>
+            <input
+              type="radio"
+              name="remote-mode"
+              value="byok"
+              bind:group={remoteMode}
+            />
+            Cloud (Deepgram)
+          </label>
+          <label>
+            <input
+              type="radio"
+              name="remote-mode"
+              value="managed"
+              bind:group={remoteMode}
+            />
+            Managed Service
+          </label>
+          <label>
+            <input
+              type="radio"
+              name="remote-mode"
+              value="local"
+              bind:group={remoteMode}
+            />
+            Local (Whisper)
+          </label>
+        </div>
+        {#if remoteMode === "byok"}
+          <div class="field">
+            <label for="byok-key">Deepgram API Key</label>
+            <input
+              id="byok-key"
+              type="password"
+              bind:value={byokApiKey}
+              placeholder="Enter your Deepgram API key"
+            />
+            <p style="font-size: 11px; color: var(--text-muted); margin-top: 4px;">
+              Get a key at <a href="https://console.deepgram.com" target="_blank" rel="noopener" style="color: var(--accent-blue);">console.deepgram.com</a>
+            </p>
+          </div>
+        {/if}
+        {#if remoteMode === "managed"}
+          <div class="field">
+            <label for="remote-url">Server URL</label>
+            <input
+              id="remote-url"
+              type="url"
+              bind:value={remoteServerUrl}
+              placeholder="wss://your-proxy.com"
+            />
+          </div>
+          <div class="managed-auth">
+            <div class="field">
+              <label for="managed-email">Email</label>
+              <input
+                id="managed-email"
+                type="email"
+                bind:value={managedEmail}
+                placeholder="email@example.com"
+              />
+            </div>
+            <div class="field">
+              <label for="managed-password">Password</label>
+              <input
+                id="managed-password"
+                type="password"
+                bind:value={managedPassword}
+              />
+            </div>
+            <div class="auth-buttons">
+              <button onclick={handleManagedLogin}>Login</button>
+              <button onclick={handleManagedRegister}>Register</button>
+            </div>
+          </div>
+        {/if}
+      </section>
+
+      {#if !isCloudMode}
+      <!-- Transcription Settings (local Whisper only) -->
       <section class="settings-section">
         <h3>Transcription Settings</h3>
         <div class="field">
@@ -473,6 +657,7 @@
           />
         </div>
       </section>
+      {/if}
 
       <!-- Display Settings -->
       <section class="settings-section">
@@ -628,11 +813,11 @@
         </div>
       </section>
 
-      <!-- Server Sync -->
+      <!-- Server Sync (Shared Captions) -->
       <section class="settings-section">
-        <h3>Server Sync</h3>
+        <h3>Shared Captions</h3>
         <div class="field-row">
-          <label for="sync-enabled">Enable Server Sync</label>
+          <label for="sync-enabled">Enable Shared Captions</label>
           <input
             id="sync-enabled"
             type="checkbox"
@@ -640,13 +825,48 @@
           />
         </div>
         {#if syncEnabled}
+          <div class="room-actions">
+            <button
+              onclick={handleCreateRoom}
+              disabled={roomCreating}
+              class="secondary"
+            >
+              {roomCreating ? "Creating..." : "Create Room"}
+            </button>
+            <div class="join-row">
+              <input
+                type="text"
+                bind:value={joinCode}
+                placeholder="Paste share code to join"
+                class="join-input"
+              />
+              <button onclick={handleJoinRoom} disabled={!joinCode.trim()} class="secondary">
+                Join
+              </button>
+            </div>
+          </div>
+
+          {#if roomCreateMessage}
+            <p class="room-message" class:error={roomCreateMessage.startsWith("Error")}>{roomCreateMessage}</p>
+          {/if}
+
+          {#if shareCode}
+            <div class="share-code-box">
+              <label>Share Code</label>
+              <div class="share-code-row">
+                <input type="text" value={shareCode} readonly class="share-code-input" />
+                <button onclick={copyShareCode} class="secondary">Copy</button>
+              </div>
+            </div>
+          {/if}
+
           <div class="field">
             <label for="sync-url">Server URL</label>
             <input
               id="sync-url"
               type="url"
               bind:value={syncUrl}
-              placeholder="http://localhost:3000/api/send"
+              placeholder="https://caption.shadowdao.com/api/send"
             />
           </div>
           <div class="field">
@@ -664,90 +884,6 @@
         {/if}
       </section>
 
-      <!-- Remote Transcription -->
-      <section class="settings-section">
-        <h3>Remote Transcription</h3>
-        <div class="radio-group">
-          <label>
-            <input
-              type="radio"
-              name="remote-mode"
-              value="local"
-              bind:group={remoteMode}
-            />
-            Local
-          </label>
-          <label>
-            <input
-              type="radio"
-              name="remote-mode"
-              value="managed"
-              bind:group={remoteMode}
-            />
-            Managed
-          </label>
-          <label>
-            <input
-              type="radio"
-              name="remote-mode"
-              value="byok"
-              bind:group={remoteMode}
-            />
-            BYOK (Bring Your Own Key)
-          </label>
-        </div>
-        {#if remoteMode === "managed"}
-          <div class="field">
-            <label for="remote-url">Server URL</label>
-            <input
-              id="remote-url"
-              type="url"
-              bind:value={remoteServerUrl}
-              placeholder="wss://your-proxy.com"
-            />
-          </div>
-        {/if}
-        {#if remoteMode === "byok"}
-          <div class="field">
-            <label for="byok-key">Deepgram API Key</label>
-            <input
-              id="byok-key"
-              type="password"
-              bind:value={byokApiKey}
-              placeholder="Enter your Deepgram API key"
-            />
-            <p style="font-size: 11px; color: var(--text-muted); margin-top: 4px;">
-              Get a key at <a href="https://console.deepgram.com" target="_blank" rel="noopener" style="color: var(--accent-blue);">console.deepgram.com</a>
-            </p>
-          </div>
-        {/if}
-        {#if remoteMode === "managed"}
-          <div class="managed-auth">
-            <div class="field">
-              <label for="managed-email">Email</label>
-              <input
-                id="managed-email"
-                type="email"
-                bind:value={managedEmail}
-                placeholder="email@example.com"
-              />
-            </div>
-            <div class="field">
-              <label for="managed-password">Password</label>
-              <input
-                id="managed-password"
-                type="password"
-                bind:value={managedPassword}
-              />
-            </div>
-            <div class="auth-buttons">
-              <button onclick={handleManagedLogin}>Login</button>
-              <button onclick={handleManagedRegister}>Register</button>
-            </div>
-          </div>
-        {/if}
-      </section>
-
       <!-- Updates -->
       <section class="settings-section">
         <h3>Updates</h3>
@@ -943,6 +1079,73 @@
     color: #f44336;
   }
 
+  .room-actions {
+    display: flex;
+    flex-direction: column;
+    gap: 8px;
+    margin-bottom: 12px;
+  }
+
+  .join-row {
+    display: flex;
+    gap: 8px;
+  }
+
+  .join-input {
+    flex: 1;
+  }
+
+  .room-message {
+    font-size: 12px;
+    color: #4CAF50;
+    margin-bottom: 8px;
+  }
+
+  .room-message.error {
+    color: #f44336;
+  }
+
+  .share-code-box {
+    margin-bottom: 12px;
+  }
+
+  .share-code-box label {
+    display: block;
+    margin-bottom: 4px;
+    font-size: 12px;
+    color: var(--text-secondary);
+  }
+
+  .share-code-row {
+    display: flex;
+    gap: 8px;
+  }
+
+  .share-code-input {
+    flex: 1;
+    font-size: 11px;
+    font-family: monospace;
+  }
+
+  .secondary {
+    background: transparent;
+    border: 1px solid var(--border-color);
+    color: var(--text-primary);
+    padding: 6px 12px;
+    border-radius: 6px;
+    cursor: pointer;
+    font-size: 13px;
+  }
+
+  .secondary:hover {
+    background: var(--bg-tertiary);
+  }
+
+  .secondary:disabled {
+    opacity: 0.5;
+    cursor: not-allowed;
+  }
+
   .danger-btn {
     background: transparent;
     border: 1px solid var(--accent-red, #f44336);

src/lib/stores/config.svelte.ts

@@ -107,7 +107,7 @@ function getDefaultConfig(): AppConfig {
     },
     server_sync: {
       enabled: false,
-      url: "http://localhost:3000/api/send",
+      url: "",
       room: "default",
       passphrase: "",
     },
@@ -128,7 +128,7 @@ function getDefaultConfig(): AppConfig {
     },
     web_server: { port: 8080, host: "127.0.0.1" },
     remote: {
-      mode: "local",
+      mode: "byok",
       server_url: "",
       auth_token: "",
       byok_api_key: "",

version.py

@@ -1,7 +1,7 @@
 """Version information for Local Transcription."""
 
-__version__ = "2.0.8"
-__version_info__ = (2, 0, 8)
+__version__ = "2.0.14"
+__version_info__ = (2, 0, 14)
 
 # Version history:
 # 1.4.0 - Auto-update feature: