mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-22 23:23:55 +08:00
hrzandGitHub
4912f385c6
* fix:连接manager后无法使用functioncallbug * fix:意图识别使用llm无法播放音乐bug * fix：manager第一图识别使用独立llm无法初始化llm的bug * fix:智能体音色未随manager生效bug * update:添加edgeTTS音色
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
import os
|
|
import uuid
|
|
import json
|
|
import base64
|
|
import requests
|
|
from datetime import datetime
|
|
from core.providers.tts.base import TTSProviderBase
|
|
|
|
|
|
class TTSProvider(TTSProviderBase):
|
|
def __init__(self, config, delete_audio_file):
|
|
super().__init__(config, delete_audio_file)
|
|
self.model = config.get("model")
|
|
self.access_token = config.get("access_token")
|
|
if config.get("private_voice"):
|
|
self.voice = config.get("private_voice")
|
|
else:
|
|
self.voice = config.get("voice")
|
|
self.response_format = config.get("response_format")
|
|
|
|
self.host = "api.coze.cn"
|
|
self.api_url = f"https://{self.host}/v1/audio/speech"
|
|
|
|
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, text, output_file):
|
|
request_json = {
|
|
"model": self.model,
|
|
"input": text,
|
|
"voice_id": self.voice,
|
|
"response_format": self.response_format,
|
|
}
|
|
headers = {
|
|
"Authorization": f"Bearer {self.access_token}",
|
|
"Content-Type": "application/json",
|
|
}
|
|
response = requests.request(
|
|
"POST", self.api_url, json=request_json, headers=headers
|
|
)
|
|
data = response.content
|
|
file_to_save = open(output_file, "wb")
|
|
file_to_save.write(data)
|