Items completed: 1. Merged PR #2 (starlette/httpx deps) 2. Fixed async race condition in multimodal_ui.py 3. Wired TTSAdapter (ElevenLabs, Azure) in API routes 4. Moved super_big_brain.py from core/ to reasoning/ (backward compat shim) 5. Added API authentication middleware (Bearer token via FUSIONAGI_API_KEY) 6. Added async adapter interface (acomplete/acomplete_structured) 7. Migrated FastAPI on_event to lifespan (fixes 20 deprecation warnings) 8. Liquid Neural Networks (continuous-time adaptive weights) 9. Quantum-AI Hybrid compute backend (simulator + optimization) 10. Embodied Intelligence / Robotics bridge (actuator + sensor protocols) 11. Consciousness Engineering (formal self-model with introspection) 12. ASI Scoring Rubric (C/A/L/N/R self-assessment harness) 13. GPU integration tests for TensorFlow backend 14. Multi-stage production Dockerfile 15. Gitea CI/CD pipeline (lint, test matrix, Docker build) 16. API rate limiting middleware (per-IP sliding window) 17. OpenAPI docs cleanup (auth + rate limiting descriptions) 18. Benchmarking suite (decomposition, multi-path, recomposition, e2e) 19. Plugin system (head registry for custom heads) 427 tests passing, 0 ruff errors, 0 mypy errors. Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
70 lines
1.9 KiB
Python
70 lines
1.9 KiB
Python
"""TTS synthesis routes for per-head voice output."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
|
|
from fusionagi.api.dependencies import get_session_store
|
|
from fusionagi.config.head_voices import get_voice_id_for_head
|
|
from fusionagi.schemas.head import HeadId
|
|
|
|
router = APIRouter()
|
|
|
|
_tts_adapter: Any = None
|
|
|
|
|
|
def set_tts_adapter(adapter: Any) -> None:
|
|
"""Set the global TTS adapter for synthesis routes."""
|
|
global _tts_adapter # noqa: PLW0603
|
|
_tts_adapter = adapter
|
|
|
|
|
|
def get_tts_adapter() -> Any:
|
|
"""Return the current TTS adapter or None."""
|
|
return _tts_adapter
|
|
|
|
|
|
@router.post("/{session_id}/synthesize")
|
|
async def synthesize(
|
|
session_id: str,
|
|
body: dict[str, Any],
|
|
) -> dict[str, Any]:
|
|
"""Synthesize text to audio for a head.
|
|
|
|
Body: ``{ "text": "...", "head_id": "logic" }``
|
|
|
|
Returns: ``{ "audio_base64": "..." }`` or ``{ "audio_base64": null }``
|
|
if TTS not configured.
|
|
"""
|
|
store = get_session_store()
|
|
if not store:
|
|
raise HTTPException(status_code=503, detail="Service not initialized")
|
|
sess = store.get(session_id)
|
|
if not sess:
|
|
raise HTTPException(status_code=404, detail="Session not found")
|
|
|
|
text = body.get("text", "")
|
|
head_id_str = body.get("head_id", "")
|
|
if not text:
|
|
raise HTTPException(status_code=400, detail="text is required")
|
|
|
|
try:
|
|
head_id = HeadId(head_id_str)
|
|
except ValueError:
|
|
head_id = HeadId.LOGIC
|
|
|
|
voice_id = get_voice_id_for_head(head_id)
|
|
audio_base64: str | None = None
|
|
|
|
adapter = get_tts_adapter()
|
|
if adapter is not None:
|
|
audio_bytes = await adapter.synthesize(text, voice_id=voice_id)
|
|
if audio_bytes:
|
|
import base64
|
|
|
|
audio_base64 = base64.b64encode(audio_bytes).decode()
|
|
|
|
return {"audio_base64": audio_base64, "voice_id": voice_id}
|