Jamie Pine
b434db22f6
The suite hadn't run green since the routes refactor: - test_profile_duplicate_names.py imported the pre-refactor module layout and broke collection; now imports backend.services.profiles - tests/conftest.py puts the repo root and backend dir on sys.path so files collect standalone instead of depending on run order - test_cors.py tested a hand-copied mirror of the origin list that had drifted from app.py (missing http://tauri.localhost); it now builds the app via the real create_app() factory - test_progress.py simulated a 1KB download, below the tracker's 1MB reporting threshold; simulation raised to 5MB - slow/timeout markers registered in pyproject Ruff: ~900 violations auto-fixed (typing modernization, import sorting, unused imports, whitespace). The remaining rules are baselined in pyproject.toml with per-rule counts to burn down, plus per-file carve-outs for deliberate env-before-import ordering. ruff check is now clean; suite is 134 passed, 2 skipped.
Voicebox MCP server
Local Model Context Protocol server — lets any MCP-aware agent (Claude Code, Cursor, Windsurf, VS Code MCP extensions, etc.) speak text in your cloned voices, transcribe audio, and browse captures.
The server runs inside the same uvicorn process as the rest of Voicebox
and is mounted at /mcp (Streamable HTTP transport).
Install into your agent
Preferred — direct HTTP:
{
"mcpServers": {
"voicebox": {
"url": "http://127.0.0.1:17493/mcp",
"headers": { "X-Voicebox-Client-Id": "claude-code" }
}
}
}
Fallback — stdio shim (when the client doesn't speak HTTP MCP). The
voicebox-mcp binary ships inside the Voicebox.app bundle:
{
"mcpServers": {
"voicebox": {
"command": "/Applications/Voicebox.app/Contents/MacOS/voicebox-mcp",
"env": { "VOICEBOX_CLIENT_ID": "claude-code" }
}
}
}
Claude Code one-liner:
claude mcp add voicebox \
--transport http \
--url http://127.0.0.1:17493/mcp \
--header "X-Voicebox-Client-Id: claude-code"
Tools
| Name | Purpose |
|---|---|
voicebox.speak |
Speak text in a voice profile. Returns a generation id you can poll. |
voicebox.transcribe |
Whisper transcription of a base64 blob or an absolute local path. |
voicebox.list_captures |
Recent captures (dictation / recording / file) with transcripts. |
voicebox.list_profiles |
Available voice profiles (cloned + preset). |
All tools resolve voice profiles in this precedence:
- Explicit
profilearg (name or id — case-insensitive) - Per-client binding keyed by
X-Voicebox-Client-Id capture_settings.default_playback_voice_id(global default)
Bindings are managed via GET|PUT /mcp/bindings or in the app under
Settings → MCP.
Debug with MCP Inspector
npx @modelcontextprotocol/inspector http://127.0.0.1:17493/mcp
Point it at the URL, hit "List tools," call voicebox.list_profiles
first to confirm wiring, then voicebox.speak for end-to-end.
Non-MCP REST surface
POST /speak is a thin wrapper on the same code path for callers that
don't speak MCP (shell scripts, ACP, A2A):
curl -X POST http://127.0.0.1:17493/speak \
-H 'Content-Type: application/json' \
-H 'X-Voicebox-Client-Id: claude-code' \
-d '{"text":"Build complete.","profile":"Morgan"}'
Code layout
backend/mcp_server/
├── __init__.py # re-export mount_into
├── server.py # build_mcp_server() + mount_into(app)
├── tools.py # @mcp.tool() implementations
├── context.py # ClientIdMiddleware + current_client_id ContextVar
├── resolve.py # profile resolution precedence
├── events.py # pub/sub queue for /events/speak pill SSE
└── README.md # you are here
backend/mcp_shim/ # stdio ↔ Streamable-HTTP proxy (see its README)
The package is mcp_server, not mcp, to avoid shadowing the
installed mcp PyPI package that FastMCP imports internally.