chore: bump sidecar version to 1.0.15 [skip ci]

Engines now read user.name from the config object at transcription time
instead of caching it at init, so name changes take effect immediately.

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

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

@@ -46,8 +46,45 @@ jobs:
         shell: powershell
         run: npm ci
 
+      - name: Setup Azure Artifact Signing
+        shell: powershell
+        env:
+          AZURE_CLIENT_ID: ${{ secrets.AZURE_CLIENT_ID }}
+          AZURE_SIGNING_ENDPOINT: ${{ secrets.AZURE_SIGNING_ENDPOINT }}
+          AZURE_SIGNING_ACCOUNT: ${{ secrets.AZURE_SIGNING_ACCOUNT }}
+          AZURE_CERT_PROFILE: ${{ secrets.AZURE_CERT_PROFILE }}
+        run: |
+          if (-not $env:AZURE_CLIENT_ID) {
+            Write-Host "No Azure signing secrets configured, skipping code signing setup"
+            return
+          }
+
+          Write-Host "Setting up Azure Artifact Signing..."
+
+          # Install Artifact Signing client tools
+          nuget install Microsoft.ArtifactSigning.Client -x -OutputDirectory .\signing-tools
+          $dlibPath = (Resolve-Path ".\signing-tools\Microsoft.ArtifactSigning.Client*\bin\x64\Azure.CodeSigning.Dlib.dll").Path
+
+          # Write metadata.json
+          @{
+            Endpoint = $env:AZURE_SIGNING_ENDPOINT
+            CodeSigningAccountName = $env:AZURE_SIGNING_ACCOUNT
+            CertificateProfileName = $env:AZURE_CERT_PROFILE
+          } | ConvertTo-Json | Out-File -Encoding UTF8 metadata.json
+          $metadataPath = (Resolve-Path "metadata.json").Path
+
+          # Inject signCommand into tauri.conf.json for this build
+          $conf = Get-Content src-tauri\tauri.conf.json -Raw | ConvertFrom-Json
+          $signCmd = "signtool.exe sign /v /fd SHA256 /tr http://timestamp.acs.microsoft.com /td SHA256 /dlib `"$dlibPath`" /dmdf `"$metadataPath`" %1"
+          $conf.bundle.windows | Add-Member -NotePropertyName "signCommand" -NotePropertyValue $signCmd -Force
+          $conf | ConvertTo-Json -Depth 10 | Set-Content src-tauri\tauri.conf.json -Encoding UTF8
+
       - name: Build Tauri app
         shell: powershell
+        env:
+          AZURE_CLIENT_ID: ${{ secrets.AZURE_CLIENT_ID }}
+          AZURE_CLIENT_SECRET: ${{ secrets.AZURE_CLIENT_SECRET }}
+          AZURE_TENANT_ID: ${{ secrets.AZURE_TENANT_ID }}
         run: npm run tauri build
 
       - name: Upload to release

CLAUDE.md

@@ -11,9 +11,11 @@ Local Transcription is a cross-platform desktop application for real-time speech
 **Key Features:**
 - Cross-platform desktop app (Windows, macOS, Linux) via Tauri v2 + Svelte 5
 - Headless Python backend with FastAPI control API
-- Dual transcription modes: local Whisper or cloud Deepgram (managed/BYOK)
+- Cloud-first: defaults to Deepgram (BYOK) transcription; local Whisper also supported
+- Settings UI hides local-only options (model, VAD, timing) when in cloud mode
+- Start button gated on API key / login — shows guidance if not configured
+- Shared Captions: create rooms, share via codes, join with one click (hosted at caption.shadowdao.com)
 - Built-in web server for OBS browser source at `http://localhost:8080`
-- Optional multi-user sync via Node.js server
 - CUDA, MPS (Apple Silicon), and CPU support
 - Auto-updates, custom fonts, configurable colors
 
@@ -273,9 +275,29 @@ All per-OS build workflows can be re-run independently via `workflow_dispatch` w
 - `Info.plist` must include `NSMicrophoneUsageDescription` for mic access
 - No CUDA builds — CPU/MPS only
 
+## Code Signing
+
+Code signing is configured for Windows and macOS to eliminate install warnings (SmartScreen / Gatekeeper). See [SIGNING.md](SIGNING.md) for full setup details.
+
+**Status (as of 2026-04-10):** CI workflow changes are committed. Waiting on identity verification for both platforms before secrets can be configured.
+
+**How it works:**
+- macOS: Tauri auto-signs when `APPLE_CERTIFICATE` and related env vars are set in CI. Notarization uses App Store Connect API key.
+- Windows: Azure Artifact Signing via `signtool.exe` + dlib. CI workflow injects `signCommand` into `tauri.conf.json` at build time when `AZURE_CLIENT_ID` is set.
+- Both are no-ops when secrets aren't configured — unsigned builds work as before.
+
+**Key files:**
+- `src-tauri/Entitlements.plist` — macOS hardened runtime entitlements (mic, network)
+- `src-tauri/Info.plist` — macOS microphone usage description
+- `.gitea/workflows/build-app-macos.yml` — Apple signing + notarization
+- `.gitea/workflows/build-app-windows.yml` — Azure Artifact Signing
+
+**Secrets required (12 total):** See [SIGNING.md](SIGNING.md) for the full list — 6 Apple secrets, 6 Azure secrets.
+
 ## Related Documentation
 
 - [README.md](README.md) — User-facing documentation
 - [BUILD.md](BUILD.md) — Detailed build instructions
 - [INSTALL.md](INSTALL.md) — Installation guide
+- [SIGNING.md](SIGNING.md) — Code signing setup guide
 - [server/nodejs/README.md](server/nodejs/README.md) — Node.js server setup

README.md

@@ -7,14 +7,14 @@ A real-time speech-to-text desktop application for streamers. Runs locally on yo
 ## Features
 
 - **Real-Time Transcription**: Live speech-to-text using Whisper models with minimal latency
+- **Cloud-First**: Defaults to Deepgram cloud transcription — get started with just an API key
 - **Cross-Platform**: Native desktop app for Windows, macOS, and Linux via [Tauri](https://tauri.app/)
-- **Dual Transcription Modes**: Local (Whisper) or cloud (Deepgram) with managed billing or BYOK
-- **CPU & GPU Support**: Automatic detection of CUDA (NVIDIA), MPS (Apple Silicon), or CPU fallback
-- **Advanced Voice Detection**: Dual-layer VAD (WebRTC + Silero) for accurate speech detection
+- **Dual Transcription Modes**: Cloud (Deepgram) or local (Whisper) with automatic GPU/CPU detection
+- **Shared Captions**: Create a room and share a code so others can join — no server setup needed
 - **OBS Integration**: Built-in web server for browser source capture at `http://localhost:8080`
-- **Multi-User Sync**: Optional Node.js server to sync transcriptions across multiple users
 - **Custom Fonts**: Support for system fonts, web-safe fonts, Google Fonts, and custom font files
 - **Customizable Colors**: User-configurable colors for name, text, and background
+- **Advanced Voice Detection**: Dual-layer VAD (WebRTC + Silero) for accurate speech detection
 - **Noise Suppression**: Built-in audio preprocessing to reduce background noise
 - **Auto-Updates**: Automatic update checking with release notes display
 
@@ -87,27 +87,30 @@ For detailed build instructions, see [BUILD.md](BUILD.md).
 
 ## Usage
 
-### Standalone Mode
+### Quick Setup (Cloud — Recommended)
 
 1. Launch the application
-2. Select your microphone from the audio device dropdown
-3. Choose a Whisper model (smaller = faster, larger = more accurate):
+2. Open **Settings** — the transcription mode defaults to **Cloud (Deepgram)**
+3. Get a free API key at [console.deepgram.com](https://console.deepgram.com) and paste it in Settings
+4. Select your microphone from the audio device dropdown
+5. Click **Start Transcription**
+6. Transcriptions appear in the main window and at `http://localhost:8080`
+
+> The Start button is disabled until an API key is entered. Local-only settings (model, VAD, timing) are hidden in cloud mode to keep things simple.
+
+### Local Mode (Whisper)
+
+For offline/on-device transcription, switch to **Local (Whisper)** in Settings:
+
+1. Choose a Whisper model (smaller = faster, larger = more accurate):
    - `tiny.en` / `tiny` — Fastest, good for quick captions
    - `base.en` / `base` — Balanced speed and accuracy
    - `small.en` / `small` — Better accuracy
    - `medium.en` / `medium` — High accuracy
    - `large-v3` — Best accuracy (requires more resources)
-4. Click **Start** to begin transcription
-5. Transcriptions appear in the main window and at `http://localhost:8080`
-
-### Remote Transcription (Deepgram)
-
-Instead of local Whisper models, you can use cloud-based transcription:
-
-- **Managed mode**: Sign up via the transcription proxy for metered billing
-- **BYOK mode**: Bring your own Deepgram API key for direct access
-
-Configure in Settings > Remote Transcription.
+2. Select compute device (Auto/CUDA/CPU) and compute type
+3. Tune VAD sensitivity and timing settings as needed
+4. Click **Start Transcription**
 
 ### OBS Browser Source Setup
 
@@ -117,18 +120,42 @@ Configure in Settings > Remote Transcription.
 4. Set dimensions (e.g., 1920x300)
 5. Check "Shutdown source when not visible" for performance
 
-### Multi-User Mode (Optional)
+### Shared Captions (Multi-User)
 
-For syncing transcriptions across multiple users (e.g., multi-host streams or translation teams):
+Share live captions across multiple users using the hosted service at `https://caption.shadowdao.com/` — no server setup required.
 
-1. Deploy the Node.js server (see [server/nodejs/README.md](server/nodejs/README.md))
-2. In the app settings, enable **Server Sync**
-3. Enter the server URL (e.g., `http://your-server:3000/api/send`)
-4. Set a room name and passphrase (shared with other users)
-5. In OBS, use the server's display URL with your room name:
-   ```
-   http://your-server:3000/display?room=YOURROOM&timestamps=true&maxlines=50
-   ```
+#### Creating a Room
+
+1. Open **Settings** and enable **Shared Captions**
+2. Click **Create Room** — this generates a room name and passphrase automatically
+3. A **share code** is generated and copied to your clipboard
+4. Send the share code to anyone who should join
+
+#### Joining a Room
+
+1. Open **Settings** and enable **Shared Captions**
+2. Paste the share code you received into the **"Paste share code to join"** field
+3. Click **Join** — the server URL, room, and passphrase are auto-filled
+4. Click **Save**
+
+#### Sharing an Existing Room
+
+If you already have a room configured and want to invite others:
+
+1. Open **Settings** and scroll to **Shared Captions**
+2. Click **Share Current Room** — generates a share code from your current config and copies it to the clipboard
+3. Send the code to others
+
+#### OBS Display for Shared Rooms
+
+In OBS, add a Browser source pointing to the server's display URL:
+```
+https://caption.shadowdao.com/display?room=YOURROOM&timestamps=true&maxlines=50
+```
+
+#### Self-Hosting
+
+You can also self-host the sync server. See [server/nodejs/README.md](server/nodejs/README.md) for setup instructions, then enter your own server URL in the Shared Captions settings.
 
 ## Configuration
 
@@ -144,7 +171,7 @@ Settings are stored at `~/.local-transcription/config.yaml` and can be modified
 | `transcription.silero_sensitivity` | VAD sensitivity (0-1, lower = more sensitive) | `0.4` |
 | `transcription.post_speech_silence_duration` | Silence before finalizing (seconds) | `0.3` |
 | `transcription.continuous_mode` | Fast speaker mode for quick talkers | `false` |
-| `remote.mode` | Transcription mode (local/managed/byok) | `local` |
+| `remote.mode` | Transcription mode (local/managed/byok) | `byok` |
 | `display.show_timestamps` | Show timestamps with transcriptions | `true` |
 | `display.fade_after_seconds` | Fade out time (0 = never) | `10` |
 | `display.font_source` | Font type (System Font/Web-Safe/Google Font/Custom File) | `System Font` |

SIGNING.md

@@ -0,0 +1,136 @@
+# Code Signing Setup
+
+This document explains how to configure code signing for Local Transcription so that Windows and macOS installers are trusted by the operating system.
+
+## Overview
+
+Without code signing:
+- **Windows**: SmartScreen shows "Windows protected your PC" warnings
+- **macOS**: Gatekeeper blocks the app — "app can't be opened because it is from an unidentified developer"
+
+The CI/CD workflows are configured to sign automatically when the required secrets are present. Without secrets, builds still work — they just produce unsigned installers.
+
+---
+
+## Windows — Azure Artifact Signing
+
+**Cost**: ~$9.99/month (up to 5,000 signatures)
+
+### 1. Create an Azure Account
+
+Sign up at https://azure.microsoft.com if you don't already have one.
+
+### 2. Set Up Artifact Signing
+
+1. In the Azure Portal, search for **Artifact Signing**
+2. Create a new **Artifact Signing Account**
+   - Choose a region (e.g., West US 2) — note this for the endpoint URL
+   - The endpoint will be like `https://wus2.codesigning.azure.net/`
+3. Complete **Identity Verification** (required before you can create certificate profiles)
+4. Create a **Certificate Profile** with type "Public Trust" for code signing
+
+### 3. Create an App Registration (Service Principal)
+
+This allows CI to authenticate to Azure:
+
+1. Go to **Azure Active Directory** > **App registrations** > **New registration**
+2. Name it (e.g., `local-transcription-signing`)
+3. After creation, note the **Application (client) ID** and **Directory (tenant) ID**
+4. Go to **Certificates & secrets** > **New client secret** — note the secret value
+5. Grant the app registration the **Artifact Signing Certificate Profile Signer** role on your Artifact Signing Account
+
+### 4. Add Gitea Secrets
+
+In your Gitea repository, go to **Settings** > **Actions** > **Secrets** and add:
+
+| Secret Name | Value |
+|-------------|-------|
+| `AZURE_CLIENT_ID` | App registration Application (client) ID |
+| `AZURE_CLIENT_SECRET` | App registration client secret value |
+| `AZURE_TENANT_ID` | Directory (tenant) ID |
+| `AZURE_SIGNING_ENDPOINT` | Artifact Signing endpoint URL (e.g., `https://wus2.codesigning.azure.net/`) |
+| `AZURE_SIGNING_ACCOUNT` | Artifact Signing account name |
+| `AZURE_CERT_PROFILE` | Certificate profile name |
+
+---
+
+## macOS — Apple Developer Code Signing + Notarization
+
+**Cost**: $99/year (Apple Developer Program)
+
+### 1. Enroll in the Apple Developer Program
+
+Sign up at https://developer.apple.com/programs/
+
+### 2. Create a Developer ID Certificate
+
+1. Open **Xcode** > **Settings** > **Accounts** > select your team > **Manage Certificates**
+2. Click **+** > **Developer ID Application**
+3. Or create via the Apple Developer portal: **Certificates, Identifiers & Profiles** > **Certificates** > **+** > **Developer ID Application**
+
+### 3. Export the Certificate as .p12
+
+1. Open **Keychain Access**
+2. Find your **Developer ID Application** certificate
+3. Right-click > **Export** > save as `.p12` with a password
+4. Base64-encode it:
+   ```bash
+   base64 -i certificate.p12 | tr -d '\n'
+   ```
+
+### 4. Create an App Store Connect API Key
+
+This is used for notarization (submitting the app to Apple for verification):
+
+1. Go to https://appstoreconnect.apple.com/access/integrations/api
+2. Click **Generate API Key**
+3. Give it a name and **Developer** role (minimum)
+4. Download the `.p8` private key file (you can only download it once)
+5. Note the **Key ID** and **Issuer ID** shown on the page
+
+### 5. Find Your Signing Identity
+
+Your signing identity looks like:
+```
+Developer ID Application: Your Name (TEAMID)
+```
+
+You can find it by running:
+```bash
+security find-identity -v -p codesigning
+```
+
+### 6. Add Gitea Secrets
+
+| Secret Name | Value |
+|-------------|-------|
+| `APPLE_CERTIFICATE` | Base64-encoded .p12 certificate (from step 3) |
+| `APPLE_CERTIFICATE_PASSWORD` | Password used when exporting the .p12 |
+| `APPLE_SIGNING_IDENTITY` | Full identity string (e.g., `Developer ID Application: Your Name (TEAMID)`) |
+| `APPLE_API_KEY` | App Store Connect API Key ID |
+| `APPLE_API_ISSUER` | API issuer UUID |
+| `APPLE_API_KEY_CONTENT` | Full contents of the `.p8` private key file |
+
+---
+
+## Verifying Signing Works
+
+### Trigger a Build
+
+Both build workflows use `workflow_dispatch`, so you can trigger them manually in Gitea:
+
+1. Go to **Actions** > select the workflow > **Run workflow**
+2. Enter the release tag (e.g., `v2.0.15`)
+
+### Check macOS
+
+After installing the `.dmg`, the app should open without any Gatekeeper warnings. You can also verify from the command line:
+
+```bash
+codesign -dv --verbose=4 /Applications/Local\ Transcription.app
+spctl --assess --type execute /Applications/Local\ Transcription.app
+```
+
+### Check Windows
+
+After running the `.msi` or `-setup.exe`, there should be no SmartScreen warning. The installer properties should show your organization name as the publisher.

backend/api_server.py

@@ -73,8 +73,15 @@ class APIServer:
         original_state_cb = self.controller.on_state_changed
 
         def on_state_changed(state: str, message: str):
+            # Isolate the upstream callback so a failure there (e.g. a
+            # broken stdout pipe in main_headless) cannot propagate into
+            # _set_state and tear down engine init / reload_engine /
+            # apply_settings request handling.
             if original_state_cb:
+                try:
                     original_state_cb(state, message)
+                except Exception:
+                    pass
             self._broadcast_control({"type": "state_changed", "state": state, "message": message})
 
         self.controller.on_state_changed = on_state_changed
@@ -212,7 +219,11 @@ class APIServer:
 
         @app.put("/api/config")
         async def update_config(update: ConfigUpdate):
-            engine_reloaded, message = ctrl.apply_settings(update.settings)
+            import asyncio
+            loop = asyncio.get_event_loop()
+            engine_reloaded, message = await loop.run_in_executor(
+                None, ctrl.apply_settings, update.settings
+            )
             return {
                 "status": "ok",
                 "message": message,
@@ -269,6 +280,7 @@ class APIServer:
                     data = resp.json()
                     ctrl.config.set('remote.auth_token', data.get('token', ''))
                     ctrl.config.set('remote.server_url', req.server_url)
+                    ctrl.config.set('remote.email', req.email)
                     return {"status": "ok", "token": data.get('token', '')}
                 else:
                     raise HTTPException(status_code=resp.status_code, detail=resp.text)

backend/app_controller.py

@@ -276,7 +276,6 @@ class AppController:
         self.current_model_size = model
         self.current_device_config = device_config
 
-        user_name = self.config.get('user.name', 'User')
         continuous_mode = self.config.get('transcription.continuous_mode', False)
 
         if continuous_mode:
@@ -293,7 +292,6 @@ class AppController:
         if remote_mode in ('managed', 'byok'):
             self.transcription_engine = DeepgramTranscriptionEngine(
                 config=self.config,
-                user_name=user_name,
                 input_device_index=audio_device,
             )
             self.transcription_engine.set_callbacks(
@@ -343,7 +341,7 @@ class AppController:
                 initial_prompt=self.config.get('transcription.initial_prompt', ''),
                 no_log_file=self.config.get('transcription.no_log_file', True),
                 input_device_index=audio_device,
-                user_name=user_name,
+                app_config=self.config,
             )
             self.transcription_engine.set_callbacks(
                 realtime_callback=self._on_realtime_transcription,
@@ -608,8 +606,17 @@ class AppController:
         Returns (engine_reload_needed, message).
         """
         if new_config:
-            for key, value in new_config.items():
-                self.config.set(key, value)
+            # Flatten nested dicts into dot-notation keys so we merge
+            # individual values instead of replacing entire sections
+            # (e.g. remote.mode instead of overwriting all of remote)
+            def _flatten(d, prefix=""):
+                for k, v in d.items():
+                    full_key = f"{prefix}{k}" if not prefix else f"{prefix}.{k}"
+                    if isinstance(v, dict):
+                        _flatten(v, full_key)
+                    else:
+                        self.config.set(full_key, v)
+            _flatten(new_config)
 
         # Update web server display settings
         if self.web_server:
@@ -682,6 +689,7 @@ class AppController:
             "transcription_count": len(self.transcriptions),
             "remote_mode": remote_mode,
             "server_sync_enabled": self.config.get('server_sync.enabled', False),
+            "is_cloud_only": self.is_cloud_only,
         }
 
     def get_audio_devices(self) -> list[dict]:

backend/main_headless.py

@@ -75,10 +75,16 @@ def main():
         # Create controller and initialize
         controller = AppController(config=config)
 
-        # Wire a state callback that prints the ready event
+        # Wire a state callback that prints state events for the parent
+        # process to read. Stdout writes can fail with EINVAL on Windows
+        # when the parent stops reading the sidecar pipe; swallow those
+        # so the engine state machine isn't taken down by a logging path.
         def on_state_changed(state, message):
             event = {"event": "state", "state": state, "message": message}
+            try:
                 print(json.dumps(event), flush=True)
+            except (OSError, ValueError):
+                pass
 
         controller.on_state_changed = on_state_changed
 

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

@@ -36,18 +36,16 @@ class DeepgramTranscriptionEngine:
     #  Construction / configuration
     # ------------------------------------------------------------------ #
 
-    def __init__(self, config, user_name: str = "User", input_device_index: Optional[int] = None):
+    def __init__(self, config, input_device_index: Optional[int] = None):
         """
         Initialise the engine from a :class:`client.config.Config` object.
 
         Args:
             config: Application ``Config`` instance.
-            user_name: Display name attached to transcriptions.
             input_device_index: Index of the audio input device to use
                 (``None`` for the system default).
         """
         self.config = config
-        self.user_name = user_name
         self.input_device_index = input_device_index
 
         # Mode: 'managed' (proxy) or 'byok' (direct Deepgram)
@@ -320,9 +318,13 @@ class DeepgramTranscriptionEngine:
     def _build_ws_url_and_headers(self):
         """Return ``(url, headers)`` depending on the current mode."""
         if self.mode == "managed":
-            # Ensure the server URL uses wss:// and append the path
+            # Convert HTTP(S) URLs to WS(S) for WebSocket connection
             url = self.server_url.rstrip("/")
-            if not url.startswith("ws://") and not url.startswith("wss://"):
+            if url.startswith("https://"):
+                url = "wss://" + url[len("https://"):]
+            elif url.startswith("http://"):
+                url = "ws://" + url[len("http://"):]
+            elif not url.startswith("ws://") and not url.startswith("wss://"):
                 url = f"wss://{url}"
             url = f"{url}/ws/transcribe"
             return url, {}
@@ -450,7 +452,7 @@ class DeepgramTranscriptionEngine:
                     text=text,
                     is_final=is_final,
                     timestamp=datetime.now(),
-                    user_name=self.user_name,
+                    user_name=self.config.get('user.name', 'User'),
                 )
                 if is_final:
                     if self.final_callback:
@@ -501,7 +503,7 @@ class DeepgramTranscriptionEngine:
                     text=transcript,
                     is_final=is_final,
                     timestamp=datetime.now(),
-                    user_name=self.user_name,
+                    user_name=self.config.get('user.name', 'User'),
                 )
                 if is_final:
                     if self.final_callback:
@@ -532,10 +534,6 @@ class DeepgramTranscriptionEngine:
                 pass
             self._ws = None
 
-    def set_user_name(self, user_name: str):
-        """Update the user name attached to future transcriptions."""
-        self.user_name = user_name
-
     def is_recording_active(self) -> bool:
         """Return ``True`` if audio is currently being captured."""
         return self._is_recording

client/transcription_engine_realtime.py

@@ -58,8 +58,8 @@ class RealtimeTranscriptionEngine:
         no_log_file: bool = True,
         # Audio device
         input_device_index: Optional[int] = None,
-        # User name
-        user_name: str = ""
+        # App config (for reading user.name at transcription time)
+        app_config=None
     ):
         """
         Initialize RealtimeSTT transcription engine.
@@ -82,7 +82,7 @@ class RealtimeTranscriptionEngine:
             initial_prompt: Optional prompt to guide transcription
             no_log_file: Disable RealtimeSTT logging
             input_device_index: Audio input device index
-            user_name: User name for transcriptions
+            app_config: App Config object for reading user.name dynamically
         """
         self.model = model
         self.language = language
@@ -100,7 +100,7 @@ class RealtimeTranscriptionEngine:
         self.enable_realtime = enable_realtime_transcription
         self.realtime_model = realtime_model
         self.realtime_processing_pause = realtime_processing_pause
-        self.user_name = user_name
+        self.app_config = app_config
 
         # Callbacks
         self.realtime_callback: Optional[Callable[[TranscriptionResult], None]] = None
@@ -162,6 +162,11 @@ class RealtimeTranscriptionEngine:
         self.realtime_callback = realtime_callback
         self.final_callback = final_callback
 
+    def _get_user_name(self) -> str:
+        if self.app_config:
+            return self.app_config.get('user.name', '')
+        return ''
+
     def _on_realtime_transcription(self, text: str):
         """Internal callback for realtime transcriptions."""
         if self.realtime_callback and text.strip():
@@ -169,7 +174,7 @@ class RealtimeTranscriptionEngine:
                 text=text,
                 is_final=False,
                 timestamp=datetime.now(),
-                user_name=self.user_name
+                user_name=self._get_user_name()
             )
             self.realtime_callback(result)
 
@@ -180,7 +185,7 @@ class RealtimeTranscriptionEngine:
                 text=text,
                 is_final=True,
                 timestamp=datetime.now(),
-                user_name=self.user_name
+                user_name=self._get_user_name()
             )
             self.final_callback(result)
 
@@ -406,10 +411,6 @@ class RealtimeTranscriptionEngine:
         if self.is_recording:
             print("VAD settings updated. Restart transcription to apply changes.")
 
-    def set_user_name(self, user_name: str):
-        """Set the user name for transcriptions."""
-        self.user_name = user_name
-
     def __repr__(self) -> str:
         return f"RealtimeTranscriptionEngine(model={self.model}, device={self.device}, running={self.is_recording})"
 

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)
@@ -69,9 +69,10 @@ web_server:
   host: "127.0.0.1"
 
 remote:
-  mode: local  # local | managed | byok
-  server_url: ""  # Proxy server URL for managed mode (e.g., wss://your-proxy.com)
+  mode: byok  # local | managed | byok
+  server_url: "https://transcribe.shadowdao.com"  # Proxy server URL for managed mode
   auth_token: ""  # JWT stored after login (managed mode)
+  email: ""  # Email of the logged-in managed-mode account (for UI display)
   byok_api_key: ""  # Deepgram API key for BYOK mode
   deepgram_model: nova-2  # Deepgram model to use
   language: en-US  # Language code

gui/main_window_qt.py

@@ -401,7 +401,6 @@ class MainWindow(QMainWindow):
             # Use Deepgram-based remote transcription
             self.transcription_engine = DeepgramTranscriptionEngine(
                 config=self.config,
-                user_name=user_name,
                 input_device_index=audio_device
             )
             self.transcription_engine.set_callbacks(
@@ -431,7 +430,7 @@ class MainWindow(QMainWindow):
                 initial_prompt=self.config.get('transcription.initial_prompt', ''),
                 no_log_file=self.config.get('transcription.no_log_file', True),
                 input_device_index=audio_device,
-                user_name=user_name
+                app_config=self.config
             )
 
         # Set up callbacks for transcription results

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',

main_cli.py

@@ -90,7 +90,7 @@ class TranscriptionCLI:
             initial_prompt=self.config.get('transcription.initial_prompt', ''),
             no_log_file=True,
             input_device_index=audio_device,
-            user_name=user_name
+            app_config=self.config
         )
 
         # Set up callbacks

package.json

@@ -1,7 +1,7 @@
 {
   "name": "local-transcription",
   "private": true,
-  "version": "2.0.10",
+  "version": "2.0.20",
   "type": "module",
   "scripts": {
     "dev": "vite dev",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "local-transcription"
-version = "1.0.9"
+version = "1.0.15"
 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 = "2.0.10"
+version = "2.0.20"
 description = "Real-time speech-to-text transcription for streamers"
 authors = ["Local Transcription Contributors"]
 edition = "2021"

src-tauri/Entitlements.plist

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>com.apple.security.device.audio-input</key>
+    <true/>
+    <key>com.apple.security.network.client</key>
+    <true/>
+    <key>com.apple.security.network.server</key>
+    <true/>
+    <key>com.apple.security.cs.allow-unsigned-executable-memory</key>
+    <true/>
+</dict>
+</plist>

src-tauri/Info.plist

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>NSMicrophoneUsageDescription</key>
+    <string>Local Transcription needs microphone access for real-time speech-to-text transcription.</string>
+</dict>
+</plist>

src-tauri/src/lib.rs

@@ -74,8 +74,8 @@ pub fn run() {
         .build(tauri::generate_context!())
         .expect("error while building tauri application")
         .run(|app, event| {
-            if let tauri::RunEvent::Exit = event {
-                // Stop the sidecar when the app exits
+            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...");
@@ -83,5 +83,16 @@ pub fn run() {
                         }
                     }
                 }
+                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": "2.0.10",
+  "version": "2.0.20",
   "identifier": "net.anhonesthost.local-transcription",
   "build": {
     "frontendDist": "../dist",
@@ -33,7 +33,10 @@
       "icons/icon.icns",
       "icons/icon.ico",
       "icons/icon.png"
-    ]
+    ],
+    "windows": {
+      "digestAlgorithm": "sha256"
+    }
   },
   "plugins": {
     "shell": {

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");
@@ -8,6 +9,16 @@
   );
   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() {
@@ -20,14 +31,17 @@
       } 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: 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;
     }
   }
@@ -91,7 +105,7 @@
   <button
     class={isTranscribing ? "danger" : "primary"}
     onclick={toggleTranscription}
-    disabled={!isReady || isLoading}
+    disabled={!isReady || isLoading || !cloudConfigured}
   >
     {#if isLoading}
       ...
@@ -113,6 +127,18 @@
   {#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>
@@ -122,6 +148,18 @@
     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

@@ -44,8 +44,20 @@
   let byokApiKey = $state("");
   let managedEmail = $state("");
   let managedPassword = $state("");
+  let managedLoggedIn = $state(false);
   let autoCheckUpdates = $state(true);
 
+  let isCloudMode = $derived(remoteMode === "managed" || remoteMode === "byok");
+  let isCloudOnly = $derived(
+    computeDevices.some(d => d.id === "cloud")
+  );
+
+  // Room creation / join state
+  let shareCode = $state("");
+  let joinCode = $state("");
+  let roomCreating = $state(false);
+  let roomCreateMessage = $state("");
+
   let saving = $state(false);
   let saveMessage = $state("");
 
@@ -120,6 +132,8 @@
     remoteMode = cfg.remote.mode;
     remoteServerUrl = cfg.remote.server_url;
     byokApiKey = cfg.remote.byok_api_key ?? "";
+    managedEmail = cfg.remote.email ?? "";
+    managedLoggedIn = !!(cfg.remote.auth_token && cfg.remote.email);
     autoCheckUpdates = cfg.updates.auto_check;
   });
 
@@ -199,7 +213,7 @@
       },
       remote: {
         mode: remoteMode,
-        server_url: remoteServerUrl,
+        server_url: remoteServerUrl || MANAGED_SERVER_URL,
         byok_api_key: byokApiKey,
       },
       updates: {
@@ -244,25 +258,143 @@
     }
   }
 
+  const MANAGED_SERVER_URL = "https://transcribe.shadowdao.com";
+
+  let loginMessage = $state("");
+
   async function handleManagedLogin() {
+    loginMessage = "";
     try {
       await backendStore.apiPost("/api/login", {
         email: managedEmail,
         password: managedPassword,
+        server_url: remoteServerUrl || MANAGED_SERVER_URL,
       });
+      loginMessage = "Logged in successfully!";
+      managedPassword = "";
+      managedLoggedIn = true;
+      await configStore.fetchConfig();
     } catch (err) {
       console.error("Login failed:", err);
+      loginMessage = "Login failed. Check your email and password.";
     }
   }
 
-  async function handleManagedRegister() {
+  async function handleManagedLogout() {
     try {
-      await backendStore.apiPost("/api/register", {
-        email: managedEmail,
-        password: managedPassword,
+      await configStore.updateConfig({
+        remote: { auth_token: "", email: "" },
       });
+      managedLoggedIn = false;
+      managedPassword = "";
+      loginMessage = "";
     } catch (err) {
-      console.error("Register failed:", err);
+      console.error("Logout failed:", err);
+      loginMessage = `Error: ${err}`;
+    }
+  }
+
+  const CAPTION_SERVER = "https://caption.shadowdao.com";
+
+  function generateRandomName(): string {
+    const adjectives = ['swift', 'bright', 'cosmic', 'electric', 'turbo', 'mega', 'ultra', 'super', 'hyper', 'alpha'];
+    const nouns = ['phoenix', 'dragon', 'tiger', 'falcon', 'comet', 'storm', 'blaze', 'thunder', 'frost', 'nebula'];
+    const num = Math.floor(Math.random() * 10000);
+    return `${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 handleShareCurrentRoom() {
+    const code = encodeShareCode(syncUrl, syncRoom, syncPassphrase);
+    shareCode = code;
+    try {
+      await navigator.clipboard.writeText(code);
+      roomCreateMessage = "Share code copied to clipboard!";
+    } catch {
+      roomCreateMessage = "Share code generated. Copy it from the field below.";
+    }
+  }
+
+  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.";
     }
   }
 
@@ -327,7 +459,100 @@
         </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>
+          {#if !isCloudOnly}
+          <label>
+            <input
+              type="radio"
+              name="remote-mode"
+              value="local"
+              bind:group={remoteMode}
+            />
+            Local (Whisper)
+          </label>
+          {/if}
+        </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="managed-auth">
+            {#if managedLoggedIn}
+              <p style="font-size: 13px; margin: 0 0 8px;">
+                <span style="color: var(--accent-green, #4CAF50);">✓ Logged in</span>
+                as <strong>{managedEmail}</strong>
+              </p>
+              <div class="auth-buttons">
+                <button onclick={handleManagedLogout}>Log out</button>
+              </div>
+            {:else}
+              <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>
+              </div>
+              <p style="font-size: 11px; color: var(--text-muted); margin-top: 8px;">
+                Don't have an account? <a href="https://transcribe.shadowdao.com/register.html" target="_blank" rel="noopener" style="color: var(--accent-blue);">Sign up here</a>
+              </p>
+            {/if}
+            {#if loginMessage}
+              <p style="font-size: 12px; margin-top: 6px; color: {loginMessage.startsWith('Logged') ? 'var(--accent-green, #4CAF50)' : 'var(--accent-red, #f44336)'};">
+                {loginMessage}
+              </p>
+            {/if}
+          </div>
+        {/if}
+      </section>
+
+      {#if !isCloudMode}
+      <!-- Transcription Settings (local Whisper only) -->
       <section class="settings-section">
         <h3>Transcription Settings</h3>
         <div class="field">
@@ -473,6 +698,7 @@
           />
         </div>
       </section>
+      {/if}
 
       <!-- Display Settings -->
       <section class="settings-section">
@@ -628,11 +854,11 @@
         </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 +866,57 @@
           />
         </div>
         {#if syncEnabled}
+          <div class="room-actions">
+            <div class="room-buttons-row">
+              <button
+                onclick={handleCreateRoom}
+                disabled={roomCreating}
+                class="secondary"
+              >
+                {roomCreating ? "Creating..." : "Create Room"}
+              </button>
+              <button
+                onclick={handleShareCurrentRoom}
+                disabled={!syncUrl.trim() || !syncRoom.trim() || !syncPassphrase.trim()}
+                class="secondary"
+              >
+                Share Current Room
+              </button>
+            </div>
+            <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 +934,6 @@
         {/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 +1129,78 @@
     color: #f44336;
   }
 
+  .room-actions {
+    display: flex;
+    flex-direction: column;
+    gap: 8px;
+    margin-bottom: 12px;
+  }
+
+  .room-buttons-row {
+    display: flex;
+    gap: 8px;
+  }
+
+  .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/backend.svelte.ts

@@ -19,6 +19,7 @@ interface BackendState {
   wsConnection: WebSocket | null;
   version: string;
   lastError: string;
+  isCloudOnly: boolean;
 }
 
 let state = $state<BackendState>({
@@ -30,6 +31,7 @@ let state = $state<BackendState>({
   wsConnection: null,
   version: "1.4.0",
   lastError: "",
+  isCloudOnly: false,
 });
 
 let reconnectTimer: ReturnType<typeof setTimeout> | null = null;
@@ -72,6 +74,9 @@ async function pollStatus() {
       if (data.version) {
         state.version = data.version;
       }
+      if (data.is_cloud_only !== undefined) {
+        state.isCloudOnly = data.is_cloud_only;
+      }
     }
   } catch {
     // API not ready yet, will retry
@@ -285,6 +290,9 @@ export const backendStore = {
   get lastError() {
     return state.lastError;
   },
+  get isCloudOnly() {
+    return state.isCloudOnly;
+  },
   get apiBaseUrl() {
     return `http://localhost:${state.port}`;
   },

src/lib/stores/config.svelte.ts

@@ -65,6 +65,7 @@ export interface AppConfig {
     mode: string;
     server_url: string;
     auth_token: string;
+    email: string;
     byok_api_key: string;
     deepgram_model: string;
     language: string;
@@ -107,7 +108,7 @@ function getDefaultConfig(): AppConfig {
     },
     server_sync: {
       enabled: false,
-      url: "http://localhost:3000/api/send",
+      url: "",
       room: "default",
       passphrase: "",
     },
@@ -128,9 +129,10 @@ function getDefaultConfig(): AppConfig {
     },
     web_server: { port: 8080, host: "127.0.0.1" },
     remote: {
-      mode: "local",
+      mode: "byok",
       server_url: "",
       auth_token: "",
+      email: "",
       byok_api_key: "",
       deepgram_model: "nova-2",
       language: "en-US",

version.py

@@ -1,7 +1,7 @@
 """Version information for Local Transcription."""
 
-__version__ = "2.0.10"
-__version_info__ = (2, 0, 10)
+__version__ = "2.0.20"
+__version_info__ = (2, 0, 20)
 
 # Version history:
 # 1.4.0 - Auto-update feature: