xiaozhi-esp32-server/main/xiaozhi-server/core/providers/tts/doubao.py

import os
import uuid
import json
import base64
import requests
from datetime import datetime

from pydub import AudioSegment

from core.providers.tts.dto.dto import TTSMessageDTO, MsgType, SentenceType
from core.utils.util import check_model_key
from core.providers.tts.base import TTSProviderBase


class TTSProvider(TTSProviderBase):
    def __init__(self, config, delete_audio_file):
        super().__init__(config, delete_audio_file)
        self.appid = config.get("appid")
        self.access_token = config.get("access_token")
        self.cluster = config.get("cluster")
        self.voice = config.get("voice")
        self.api_url = config.get("api_url")
        self.authorization = config.get("authorization")
        self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
        check_model_key("TTS", self.access_token)

    def generate_filename(self, extension=".wav"):
        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")

    async def text_to_speak(self, u_id, text, is_last_text=False, is_first_text=False):
        tmp_file = self.generate_filename()
        request_json = {
            "app": {
                "appid": f"{self.appid}",
                "token": "access_token",
                "cluster": self.cluster
            },
            "user": {
                "uid": "1"
            },
            "audio": {
                "voice_type": self.voice,
                "encoding": "wav",
                "speed_ratio": 1.0,
                "volume_ratio": 1.0,
                "pitch_ratio": 1.0,
            },
            "request": {
                "reqid": str(uuid.uuid4()),
                "text": text,
                "text_type": "plain",
                "operation": "query",
                "with_frontend": 1,
                "frontend_type": "unitTson"
            }
        }

        try:
            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
            if "data" in resp.json():
                data = resp.json()["data"]
                file_to_save = open(tmp_file, "wb")
                file_to_save.write(base64.b64decode(data))
            else:
                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
        except Exception as e:
            raise Exception(f"{__name__} error: {e}")
        # 使用 pydub 读取临时文件
        audio = AudioSegment.from_file(tmp_file, format="wav")
        audio = audio.set_channels(1).set_frame_rate(16000)
        opus_datas = self.wav_to_opus_data_audio_raw(audio.raw_data)
        yield TTSMessageDTO(u_id=u_id, msg_type=MsgType.TTS_TEXT_RESPONSE, content=opus_datas, tts_finish_text=text,
                            sentence_type=SentenceType.SENTENCE_START)
        # 用完后删除临时文件
        try:
            os.remove(tmp_file)
        except FileNotFoundError:
            # 若文件不存在，忽略该异常
            pass