mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-10-03 17:15:19 -07:00
c339d2c324
Both speak surfaces built their GenerationRequest with a hardcoded "en" fallback and never consulted the resolved profile, so a profile created with language="fr" was still synthesised as English unless the caller passed language= explicitly. This hurts the MCP path most: an agent calling voicebox.speak has no way to know the bound profile's language, so it cannot pass the argument either. Every agent-triggered generation on a non-English profile came out with an English accent. The fallback chain is now explicit argument -> resolved profile's language -> "en", which matches how engine and personality already consult the resolved binding. The "en" backstop is kept so profiles with no language set behave exactly as before. Adds backend/tests/test_speak_language.py covering both surfaces: the fallback, explicit-argument precedence, and the unchanged "en" default. Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
95 lines
2.8 KiB
Python
95 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 MCPClientBinding, 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."
|
|
),
|
|
)
|
|
|
|
binding = None
|
|
if client_id:
|
|
binding = (
|
|
db.query(MCPClientBinding)
|
|
.filter(MCPClientBinding.client_id == client_id)
|
|
.first()
|
|
)
|
|
|
|
# Resolve per-client personality default when the caller didn't pin it.
|
|
personality_flag = data.personality
|
|
if personality_flag is None and binding is not None:
|
|
personality_flag = bool(binding.default_personality)
|
|
|
|
engine = data.engine
|
|
if engine is None and binding is not None:
|
|
engine = binding.default_engine
|
|
|
|
from .generations import generate_speech
|
|
|
|
generation = await generate_speech(
|
|
models.GenerationRequest(
|
|
profile_id=profile.id,
|
|
text=data.text,
|
|
language=data.language or profile.language or "en",
|
|
engine=engine,
|
|
personality=bool(personality_flag),
|
|
),
|
|
db,
|
|
)
|
|
|
|
mcp_events.publish(
|
|
"speak-start",
|
|
{
|
|
"generation_id": getattr(generation, "id", None),
|
|
"profile_name": profile.name,
|
|
"source": "rest",
|
|
"client_id": client_id,
|
|
},
|
|
)
|
|
return generation
|