life-echo/api/app/adapters/asr/tencent_asr.py

"""Tencent Cloud ASR adapter — implements ASRProvider port."""

import asyncio
import base64
from app.core.logging import get_logger

logger = get_logger(__name__)


class TencentASRProvider:
    def __init__(self, secret_id: str, secret_key: str):
        self._secret_id = secret_id
        self._secret_key = secret_key
        self._client = None

    def _get_client(self):
        if self._client is not None:
            return self._client
        try:
            from tencentcloud.asr.v20190614 import asr_client
            from tencentcloud.common import credential
            from tencentcloud.common.profile.client_profile import ClientProfile
            from tencentcloud.common.profile.http_profile import HttpProfile

            cred = credential.Credential(self._secret_id, self._secret_key)
            http_profile = HttpProfile()
            http_profile.endpoint = "asr.tencentcloudapi.com"
            client_profile = ClientProfile()
            client_profile.httpProfile = http_profile
            self._client = asr_client.AsrClient(cred, "", client_profile)
            return self._client
        except Exception as e:
            logger.error("Tencent ASR client init failed: {}", e)
            return None

    def ensure_ready(self) -> bool:
        return bool(self._secret_id and self._secret_key and self._get_client())

    async def transcribe(self, audio: bytes, format: str = "m4a") -> str:
        client = self._get_client()
        if not client:
            return "转写失败: 腾讯云 ASR 客户端未初始化（请检查密钥与依赖）"
        try:
            from tencentcloud.asr.v20190614 import models

            audio_base64 = base64.b64encode(audio).decode("utf-8")
            req = models.SentenceRecognitionRequest()
            req.EngSerViceType = "16k_zh"
            req.SourceType = 1
            # 小写；与文档一致。iOS 常见为 m4a(AAC) 容器，与 16k 引擎匹配
            req.VoiceFormat = (format or "m4a").lower()
            req.Data = audio_base64
            req.DataLen = len(audio)

            # 腾讯 SDK 为同步阻塞调用；放到线程池里避免卡住事件循环。
            resp = await asyncio.to_thread(client.SentenceRecognition, req)
            text = (resp.Result or "").strip()
            if text:
                return text
            err = getattr(resp, "Error", None) or getattr(resp, "Message", None)
            logger.warning(
                "Tencent ASR empty Result, audio_len={} format={} err={}",
                len(audio),
                req.VoiceFormat,
                err,
            )
            return (
                "转写失败: 腾讯云返回空文本（常见原因：采样率与 16k_zh 不匹配、"
                "格式不受支持或音频无效；请确认客户端为 16kHz 单声道 m4a）"
            )
        except Exception as e:
            logger.error("Tencent ASR transcribe failed: {}", e, exc_info=True)
            return f"转写失败: {e}"[:500]