feat(omnivoice): wire to asset-engine via FastAPI wrapper + reuse chatterbox voices

- app.py: thin FastAPI wrapper exposing OpenAI /v1/audio/speech (+ /v1/audio/voices, /healthz) around OmniVoice's Python API; precomputes a voice-clone prompt per voice at startup (loaded Whisper auto-transcribes each reference). Replaces the Gradio demo. - Dockerfile/compose: run the uvicorn wrapper, /healthz healthcheck, project name pinned to "omnivoice" so the asset-engine liveness probe matches. - deploy-omnivoice.yaml: stage chatterbox /refs/*.wav as clone voices (skip _* artifacts) + verify the API surface. - services.yaml: catalog entry (id omnivoice, :8199/v1/audio/speech, voice list sourced live from /v1/audio/voices) + reproducibility_audit row. Verified live on irv-ml1: /healthz ok, 33 voices loaded, test synth -> 24kHz PCM_16 WAV.
2026-06-18 23:03:20 -07:00
parent 984b72757f
commit 06eb487a26
6 changed files with 255 additions and 37 deletions
@@ -0,0 +1,111 @@
+"""Thin FastAPI wrapper exposing OmniVoice (k2-fsa/OmniVoice) as an OpenAI-style
+TTS for the asset-engine.
+
+Upstream ships only a Gradio demo; we own this wrapper (same pattern as
+stacks/index-tts/app.py). Voices are reference WAVs staged in
+${OMNIVOICE_VOICES_DIR} (the reused chatterbox /refs/*.wav). A voice-clone prompt
+is precomputed once per voice at startup (the loaded Whisper ASR auto-transcribes
+each reference) and cached, so per-request latency is just generation.
+
+Endpoints:
+  GET  /healthz            -> readiness (200 once model + >=1 voice are loaded)
+  GET  /v1/audio/voices    -> {"voices": [<name>, ...]}
+  POST /v1/audio/speech    -> {input, voice, response_format=wav} -> audio/wav
+"""
+import glob
+import io
+import logging
+import os
+from pathlib import Path
+from typing import Optional
+
+import numpy as np
+import soundfile as sf
+import torch
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import Response
+from pydantic import BaseModel
+
+from omnivoice import OmniVoice, OmniVoiceGenerationConfig
+
+logging.basicConfig(level=os.environ.get("OMNIVOICE_LOG_LEVEL", "INFO"))
+log = logging.getLogger("omnivoice-api")
+
+CKPT = os.environ.get("OMNIVOICE_CKPT", "k2-fsa/OmniVoice")
+VOICES_DIR = os.environ.get("OMNIVOICE_VOICES_DIR", "/app/voices")
+ASR_MODEL = os.environ.get("OMNIVOICE_ASR_MODEL", "openai/whisper-large-v3-turbo")
+NUM_STEP = int(os.environ.get("OMNIVOICE_NUM_STEP", "32"))
+GUIDANCE = float(os.environ.get("OMNIVOICE_GUIDANCE_SCALE", "2.0"))
+
+app = FastAPI(title="OmniVoice TTS (asset-engine wrapper)")
+
+MODEL: Optional[OmniVoice] = None
+PROMPTS: dict = {}        # voice name -> VoiceClonePrompt
+SR: int = 24000
+
+
+class SpeechRequest(BaseModel):
+    input: str
+    voice: str
+    response_format: str = "wav"
+    model: Optional[str] = None       # ignored (single model); OpenAI-compat field
+
+
+@app.on_event("startup")
+def _load() -> None:
+    global MODEL, SR
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    log.info("loading OmniVoice %s on %s (asr=%s)", CKPT, device, ASR_MODEL)
+    MODEL = OmniVoice.from_pretrained(
+        CKPT, device_map=device, load_asr=True, asr_model_name=ASR_MODEL
+    )
+    SR = int(getattr(MODEL, "sampling_rate", 24000))
+
+    for wav in sorted(glob.glob(os.path.join(VOICES_DIR, "*.wav"))):
+        name = Path(wav).stem
+        if name.startswith("_"):
+            continue          # skip _*.wav (chatterbox test/deploy artifacts)
+        try:
+            PROMPTS[name] = MODEL.create_voice_clone_prompt(ref_audio=wav)
+            log.info("voice ready: %s", name)
+        except Exception as exc:                          # noqa: BLE001
+            log.warning("voice %s failed to load: %s", name, exc)
+    log.info("%d voices loaded: %s", len(PROMPTS), sorted(PROMPTS))
+
+
+@app.get("/healthz")
+def healthz():
+    if MODEL is None or not PROMPTS:
+        raise HTTPException(status_code=503, detail="not ready")
+    return {"status": "ok", "voices": len(PROMPTS), "sampling_rate": SR}
+
+
+@app.get("/v1/audio/voices")
+def voices():
+    return {"voices": sorted(PROMPTS.keys())}
+
+
+@app.post("/v1/audio/speech")
+def speech(req: SpeechRequest):
+    if MODEL is None:
+        raise HTTPException(status_code=503, detail="model not loaded")
+    if not req.input or not req.input.strip():
+        raise HTTPException(status_code=400, detail="input is empty")
+    if req.response_format not in ("wav", "", None):
+        raise HTTPException(status_code=400, detail="only response_format=wav is supported")
+
+    prompt = PROMPTS.get(req.voice)
+    if prompt is None:
+        raise HTTPException(
+            status_code=404,
+            detail=f"unknown voice '{req.voice}'; have {sorted(PROMPTS)}",
+        )
+
+    gen = OmniVoiceGenerationConfig(num_step=NUM_STEP, guidance_scale=GUIDANCE, denoise=True)
+    out = MODEL.generate(text=req.input.strip(), voice_clone_prompt=prompt, generation_config=gen)
+    audio = out[0] if isinstance(out, (list, tuple)) else out
+    audio = np.asarray(audio, dtype=np.float32)
+
+    buf = io.BytesIO()
+    sf.write(buf, audio, SR, format="WAV", subtype="PCM_16")
+    return Response(content=buf.getvalue(), media_type="audio/wav")