"""Teste de fumaça do serviço de voz rodando (porta 4510): status, síntese de cada voz e transcrição com tempos. Uso: voice/.venv/Scripts/python voice/scripts/smoke.py [--out output/voice-smoke] Lê a chave do voice/.env. Grava os WAV gerados e o JSON da transcrição na pasta de saída. """ from __future__ import annotations import argparse import json import os import sys import time import urllib.error import urllib.request from pathlib import Path VOICE_ROOT = Path(__file__).resolve().parent.parent sys.path.insert(0, str(VOICE_ROOT)) from app.config import PROJECT_ROOT, load_dotenv # noqa: E402 TEXT = "Olá! Este é o serviço de voz do CenaForge, gerando a narração do episódio." def call(method: str, path: str, key: str, port: int, body: bytes | None = None, headers: dict | None = None): request = urllib.request.Request( f"http://127.0.0.1:{port}{path}", data=body, method=method, headers={"X-Service-Key": key, **(headers or {})}, ) try: with urllib.request.urlopen(request, timeout=300) as response: # noqa: S310 - localhost fixo return response.status, {k.lower(): v for k, v in response.headers.items()}, response.read() except urllib.error.HTTPError as error: return error.code, {k.lower(): v for k, v in error.headers.items()}, error.read() def main() -> int: parser = argparse.ArgumentParser() parser.add_argument("--out", default=str(PROJECT_ROOT / "output" / "voice-smoke")) parser.add_argument("--detail", default="words", choices=("text", "segments", "words")) args = parser.parse_args() load_dotenv(VOICE_ROOT / ".env") key = os.environ["VOICE_SERVICE_KEY"] port = int(os.environ.get("VOICE_PORT", "4510")) out = Path(args.out) out.mkdir(parents=True, exist_ok=True) status, _, raw = call("GET", "/v1/status", key, port) data = json.loads(raw) print(f"status {status}: dispositivo={data['device']} rvc={data['rvc']} motores={data['engines']}") voices = json.loads(call("GET", "/v1/voices", key, port)[2])["items"] first_wav: Path | None = None for voice in voices: request_id = f"smoke-{voice['id']}-{int(time.time())}" payload = {"requestId": request_id[:64], "text": TEXT, "voiceId": voice["id"], "params": {"format": "wav"}} started = time.perf_counter() code, headers, audio = call( "POST", "/v1/synthesize", key, port, json.dumps(payload).encode(), {"Content-Type": "application/json"} ) wall = time.perf_counter() - started if code != 200: print(f" {voice['id']}: ERRO {code} {audio[:200]!r}") continue target = out / f"{voice['id']}.wav" target.write_bytes(audio) first_wav = first_wav or target print(f" {voice['id']} ({voice.get('provider')}): {headers.get('x-audio-duration-ms')} ms de áudio " f"em {wall:.2f} s -> {target}") if first_wav is None: print("nenhuma voz gerou áudio") return 1 audio = first_wav.read_bytes() duration_ms = max(1, int((len(audio) - 44) / 2 / 24000 * 1000)) # WAV PCM16 mono; só uma estimativa started = time.perf_counter() code, _, raw = call("POST", "/v1/transcribe", key, port, audio, { "Content-Type": "audio/wav", "X-Idempotency-Key": f"smoke-{int(time.time())}", "X-Audio-Duration-Ms": str(duration_ms), "X-Language": "pt-BR", "X-Detail": args.detail, }) result = json.loads(raw) while code == 202: time.sleep(result["retryAfterMs"] / 1000) code, _, raw = call("GET", f"/v1/transcribe/jobs/{result['jobRef']}", key, port) result = json.loads(raw) wall = time.perf_counter() - started (out / "transcribe.json").write_text(json.dumps(result, ensure_ascii=False, indent=2), encoding="utf-8") print(f"transcrição {code} em {wall:.2f} s: {result.get('text')!r}") if result.get("segments"): words = [w for s in result["segments"] for w in s.get("words", [])] print(f" {len(result['segments'])} segmento(s), {len(words)} palavra(s) com tempo") return 0 if code == 200 else 1 if __name__ == "__main__": raise SystemExit(main())