mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-19 06:40:38 -07:00
James PineandClaude Opus 4.7
0cef2c9fe1
Mounts FastMCP at /mcp (Streamable HTTP) so Claude Code, Cursor, Windsurf, and the VS Code MCP extensions can call voicebox.speak, voicebox.transcribe, voicebox.list_captures, and voicebox.list_profiles against the running Voicebox server. Backend - new backend/mcp_server package (tools, middleware, profile resolve, pub/sub events); named mcp_server to avoid shadowing the installed mcp PyPI package FastMCP imports internally - app.py migrated from @app.on_event to lifespan= so FastMCP's session manager cohabits with Voicebox's startup/shutdown - new MCPClientBinding table + /mcp/bindings CRUD; ClientIdMiddleware reads X-Voicebox-Client-Id into a ContextVar and stamps last_seen_at - profile resolution precedence: explicit -> per-client binding -> capture_settings.default_playback_voice_id - POST /speak REST wrapper for non-MCP callers (shell, ACP, A2A) - GET /events/speak SSE broadcasts speak-start / speak-end so the pill surfaces agent-initiated speech - backend/mcp_shim proxy (plain httpx) for stdio-only MCP clients - PyInstaller spec updates + new --shim build target (~18 MB) Frontend - Settings -> MCP page with HTTP / stdio / claude-mcp-add copy snippets, default voice picker, per-client bindings table, connection status - useMCPBindings, useSpeakEvents hooks - CapturePill gains 'speaking' state; DictateWindow subscribes to SSE and emits dictate:show so the Rust side surfaces the pill window Native - tauri.conf.json externalBin now includes voicebox-mcp - show_dictate_window helper + dictate:show listener in main.rs - (also in this commit: InputMonitoringGate UX, hotkey_monitor tweaks, landing footer/navbar updates, new overview docs for captures / dictation / mcp-server / voice-personalities) Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
94 lines
2.8 KiB
Python
94 lines
2.8 KiB
Python
"""POST /speak — REST wrapper around voicebox.speak for non-MCP callers.
|
|
|
|
Shell scripts, ACP, A2A, or any agent that doesn't speak MCP can hit this
|
|
endpoint to play text through a cloned voice. Uses the same profile
|
|
resolution and generation pipeline as the MCP tool, so per-client
|
|
bindings (via X-Voicebox-Client-Id) work identically.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, Request
|
|
from sqlalchemy.orm import Session
|
|
|
|
from .. import models
|
|
from ..database import get_db
|
|
from ..mcp_server import events as mcp_events
|
|
from ..mcp_server.resolve import resolve_profile
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
@router.post("/speak", response_model=models.GenerationResponse)
|
|
async def speak(
|
|
data: models.SpeakRequest,
|
|
request: Request,
|
|
db: Session = Depends(get_db),
|
|
):
|
|
"""Speak text in a voice profile. Mirrors voicebox.speak (MCP).
|
|
|
|
Response shape matches POST /generate — a ``GenerationResponse`` with
|
|
``status="generating"`` and an ``id`` the caller polls at
|
|
``GET /generate/{id}/status``.
|
|
"""
|
|
client_id = request.headers.get("X-Voicebox-Client-Id")
|
|
profile = resolve_profile(data.profile, client_id, db)
|
|
if profile is None:
|
|
if data.profile:
|
|
raise HTTPException(
|
|
status_code=404,
|
|
detail=f"Voice profile '{data.profile}' not found.",
|
|
)
|
|
raise HTTPException(
|
|
status_code=400,
|
|
detail=(
|
|
"No voice profile resolved. Pass `profile` (name or id), "
|
|
"or configure a default in Voicebox → Settings → MCP."
|
|
),
|
|
)
|
|
|
|
# Persona path if intent requested AND profile has a personality prompt.
|
|
if data.intent is not None and profile.personality:
|
|
from .profiles import speak_in_character
|
|
|
|
generation = await speak_in_character(
|
|
profile.id,
|
|
models.PersonalitySpeakRequest(
|
|
text=data.text,
|
|
persist=True,
|
|
language=data.language,
|
|
engine=data.engine,
|
|
intent=data.intent,
|
|
),
|
|
db,
|
|
)
|
|
else:
|
|
# Plain TTS path — matches POST /generate.
|
|
from .generations import generate_speech
|
|
|
|
generation = await generate_speech(
|
|
models.GenerationRequest(
|
|
profile_id=profile.id,
|
|
text=data.text,
|
|
language=data.language or "en",
|
|
engine=data.engine or "qwen",
|
|
),
|
|
db,
|
|
)
|
|
|
|
mcp_events.publish(
|
|
"speak-start",
|
|
{
|
|
"generation_id": getattr(generation, "id", None),
|
|
"profile_name": profile.name,
|
|
"source": "rest",
|
|
"client_id": client_id,
|
|
},
|
|
)
|
|
return generation
|