chore: bump sidecar version to 1.0.7 [skip ci]

CUDA sidecars are ~2GB and too slow to upload from the Windows runner.
Cloud (Deepgram) provides faster transcription anyway. Removed:

- CUDA build steps from Windows and Linux sidecar workflows
- CUDA option from the SidecarSetup download screen

Remaining sidecar variants:
- Cloud (Deepgram): ~50 MB - recommended for most users
- Local CPU: ~500 MB - for offline/privacy use

CUDA can be revisited once the managed Deepgram service is ready.

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

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

@@ -16,7 +16,8 @@ jobs:
       RELEASE_TAG: "${{ inputs.tag }}"
     steps:
       - name: Show tag
-        run: echo "Building for tag: ${RELEASE_TAG}"
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
 
       - uses: actions/checkout@v4
         with:

.gitea/workflows/build-app-macos.yml

@@ -16,7 +16,8 @@ jobs:
       RELEASE_TAG: "${{ inputs.tag }}"
     steps:
       - name: Show tag
-        run: echo "Building for tag: ${RELEASE_TAG}"
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
 
       - uses: actions/checkout@v4
         with:

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

@@ -16,7 +16,8 @@ jobs:
       RELEASE_TAG: "${{ inputs.tag }}"
     steps:
       - name: Show tag
-        run: echo "Building cloud sidecar for tag ${RELEASE_TAG}"
+        run: |
+          echo "Building cloud sidecar for tag ${RELEASE_TAG}"
 
       - uses: actions/checkout@v4
         with:
@@ -164,7 +165,8 @@ jobs:
       RELEASE_TAG: "${{ inputs.tag }}"
     steps:
       - name: Show tag
-        run: echo "Building cloud sidecar for tag ${RELEASE_TAG}"
+        run: |
+          echo "Building cloud sidecar for tag ${RELEASE_TAG}"
 
       - uses: actions/checkout@v4
         with:

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

@@ -16,7 +16,8 @@ jobs:
       RELEASE_TAG: "${{ inputs.tag }}"
     steps:
       - name: Show tag
-        run: echo "Building for tag: ${RELEASE_TAG}"
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
 
       - uses: actions/checkout@v4
         with:
@@ -39,26 +40,16 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y portaudio19-dev
 
-      - name: Build sidecar (CUDA)
-        run: |
-          uv sync --frozen || uv sync
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CUDA)
-        run: |
-          cd dist/local-transcription-backend && zip -r ../../sidecar-linux-x86_64-cuda.zip .
-
       - name: Build sidecar (CPU)
+        env:
+          UV_NO_SOURCES: "1"
         run: |
-          rm -rf dist/local-transcription-backend build/
-          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
-          # Run pyinstaller directly from venv to prevent uv run from
-          # re-resolving torch back to the CUDA version via pyproject.toml sources
+          uv sync
           .venv/bin/pyinstaller local-transcription-headless.spec
 
       - name: Package sidecar (CPU)
         run: |
-          cd dist/local-transcription-backend && zip -r ../../sidecar-linux-x86_64-cpu.zip .
+          cd dist/local-transcription-backend && zip -9 -r ../../sidecar-linux-x86_64-cpu.zip .
 
       - name: Upload to sidecar release
         env:

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

@@ -16,7 +16,8 @@ jobs:
       RELEASE_TAG: "${{ inputs.tag }}"
     steps:
       - name: Show tag
-        run: echo "Building for tag: ${RELEASE_TAG}"
+        run: |
+          echo "Building for tag: ${RELEASE_TAG}"
 
       - uses: actions/checkout@v4
         with:

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

@@ -54,29 +54,18 @@ jobs:
             choco install 7zip -y
           }
 
-      - name: Build sidecar (CUDA)
-        shell: powershell
-        run: |
-          uv sync --frozen
-          if ($LASTEXITCODE -ne 0) { uv sync }
-          uv run pyinstaller local-transcription-headless.spec
-
-      - name: Package sidecar (CUDA)
-        shell: powershell
-        run: |
-          7z a -tzip -mx=5 sidecar-windows-x86_64-cuda.zip .\dist\local-transcription-backend\*
-
       - name: Build sidecar (CPU)
         shell: powershell
+        env:
+          UV_NO_SOURCES: "1"
         run: |
-          Remove-Item -Recurse -Force dist\local-transcription-backend, build -ErrorAction SilentlyContinue
-          uv pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu --force-reinstall
+          uv sync
           .venv\Scripts\pyinstaller.exe local-transcription-headless.spec
 
       - name: Package sidecar (CPU)
         shell: powershell
         run: |
-          7z a -tzip -mx=5 sidecar-windows-x86_64-cpu.zip .\dist\local-transcription-backend\*
+          7z a -tzip -mx=9 sidecar-windows-x86_64-cpu.zip .\dist\local-transcription-backend\*
 
       - name: Upload to sidecar release
         shell: powershell

backend/app_controller.py

@@ -106,6 +106,12 @@ class AppController:
                 DeviceManager = None
 
         self.device_manager = DeviceManager() if DeviceManager else None
+        self.is_cloud_only = DeviceManager is None
+
+        # If this is the cloud-only sidecar and mode is still "local",
+        # auto-switch to "byok" so the engine doesn't try to load Whisper.
+        if self.is_cloud_only and self.config.get('remote.mode', 'local') == 'local':
+            self.config.set('remote.mode', 'byok')
 
         # State
         self._state = AppState.INITIALIZING
@@ -300,8 +306,17 @@ class AppController:
             # Lazy-import heavy local transcription dependencies
             global RealtimeTranscriptionEngine
             if RealtimeTranscriptionEngine is None:
+                try:
                     from client.transcription_engine_realtime import RealtimeTranscriptionEngine as _RTE
                     RealtimeTranscriptionEngine = _RTE
+                except ImportError:
+                    # Cloud-only sidecar -- local engine not available
+                    self._set_state(
+                        AppState.ERROR,
+                        "Local transcription not available in this build. "
+                        "Please switch to Cloud (Deepgram) mode in Settings."
+                    )
+                    return
 
             if self.device_manager:
                 self.device_manager.set_device(device_config)
@@ -357,6 +372,14 @@ class AppController:
                 device_display = "Unknown"
 
             self._set_state(AppState.READY, f"Ready | Device: {device_display}")
+        else:
+            # Cloud sidecar with no API key -- show helpful setup message
+            # instead of a scary error. The user needs to enter their key.
+            if self.is_cloud_only:
+                self._set_state(
+                    AppState.READY,
+                    "Setup needed: Open Settings > Remote Transcription > enter your Deepgram API key"
+                )
             else:
                 self._set_state(AppState.ERROR, message)
 

package.json

@@ -1,7 +1,7 @@
 {
   "name": "local-transcription",
   "private": true,
-  "version": "2.0.5",
+  "version": "2.0.8",
   "type": "module",
   "scripts": {
     "dev": "vite dev",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "local-transcription"
-version = "1.0.4"
+version = "1.0.7"
 description = "A standalone desktop application for real-time speech-to-text transcription using Whisper models"
 readme = "README.md"
 requires-python = ">=3.9"

src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "local-transcription"
-version = "2.0.5"
+version = "2.0.8"
 description = "Real-time speech-to-text transcription for streamers"
 authors = ["Local Transcription Contributors"]
 edition = "2021"

src-tauri/tauri.conf.json

@@ -1,6 +1,6 @@
 {
   "productName": "Local Transcription",
-  "version": "2.0.5",
+  "version": "2.0.8",
   "identifier": "net.anhonesthost.local-transcription",
   "build": {
     "frontendDist": "../dist",

src/lib/components/Controls.svelte

@@ -17,6 +17,9 @@
       } 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);
     } finally {

src/lib/components/SidecarSetup.svelte

@@ -36,11 +36,12 @@
 
     try {
       // Listen for progress events from the Tauri backend
-      unlisten = await listen<{ progress: number; message: string }>(
+      unlisten = await listen<{ downloaded: number; total: number; phase: string; message: string }>(
         "sidecar-download-progress",
         (event) => {
-          progress = event.payload.progress;
-          progressMessage = event.payload.message;
+          const { downloaded, total, message } = event.payload;
+          progress = total > 0 ? (downloaded / total) * 100 : 0;
+          progressMessage = message;
         }
       );
 
@@ -125,23 +126,6 @@
           </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-name">Local - GPU (NVIDIA CUDA)</span>
-            <span class="variant-desc">~2 GB download</span>
-            <span class="variant-detail">
-              Runs Whisper AI models locally using your NVIDIA GPU for fast
-              transcription. No internet needed after download. Requires an
-              NVIDIA GPU with CUDA support.
-            </span>
-          </div>
-        </label>
       </div>
 
       <button class="download-btn" onclick={startDownload}>

src/lib/stores/backend.svelte.ts

@@ -302,6 +302,7 @@ export const backendStore = {
   setPort,
   connect: connectWebSocket,
   disconnect,
+  pollStatus,
   apiUrl,
   apiFetch,
   apiGet,

version.py

@@ -1,7 +1,7 @@
 """Version information for Local Transcription."""
 
-__version__ = "2.0.5"
-__version_info__ = (2, 0, 5)
+__version__ = "2.0.8"
+__version_info__ = (2, 0, 8)
 
 # Version history:
 # 1.4.0 - Auto-update feature: