cfc/cfc-langgraph/app/api/audio.py

"""语音转写端点"""
import os
import uuid
import logging
from fastapi import APIRouter, UploadFile, File, HTTPException
from pydantic import BaseModel
from typing import Optional
from app.audio.transcriber import transcribe_audio

logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/v1", tags=["audio"])

MAX_FILE_SIZE = 5 * 1024 * 1024
UPLOAD_DIR = "/tmp/stt_uploads"


class TranscribeResponse(BaseModel):
    code: int = 200
    message: str = "ok"
    data: Optional[dict] = None


@router.post("/audio/transcribe", response_model=TranscribeResponse)
async def transcribe(file: UploadFile = File(...)):
    if not file.filename or not file.filename.lower().endswith((".mp3", ".wav", ".m4a", ".flac", ".ogg")):
        raise HTTPException(status_code=400, detail="不支持的音频格式，仅支持 mp3/wav/m4a/flac/ogg")
    content = await file.read()
    if len(content) > MAX_FILE_SIZE:
        raise HTTPException(status_code=413, detail="音频文件过大（最大 5MB）")
    if len(content) < 1000:
        raise HTTPException(status_code=400, detail="音频文件为空或过短")

    os.makedirs(UPLOAD_DIR, exist_ok=True)
    ext = file.filename.rsplit(".", 1)[-1]
    tmp_path = os.path.join(UPLOAD_DIR, f"{uuid.uuid4().hex}.{ext}")
    try:
        with open(tmp_path, "wb") as f:
            f.write(content)
        result = transcribe_audio(tmp_path)
        return TranscribeResponse(data=result)
    except Exception as e:
        logger.error("转写失败: %s", e, exc_info=True)
        return TranscribeResponse(code=500, message="转写失败: " + str(e), data={})
    finally:
        try:
            os.remove(tmp_path)
        except OSError:
            pass