mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-23 15:43:54 +08:00
50ecee99cc
* fix: ASR句首丢字问题 (#338) * feat: 支持dify的多轮对话, chat工作流支持持久化conversation_id #296 (#313) * TTS功能的一些修改 (#307) * fix: tts音频转码兼容 * feat: 支持自定义tts接口服务 * feat: tts超时时间作为可配置项 * feat: 自定义tts音频格式兼容 * style: 使命名更符合语义 --------- Co-authored-by: Jad <i@nocilol.me> Co-authored-by: yanyige <yige.yan@qq.com> Co-authored-by: Jad <journey.adc@gmail.com>
36 lines
1.3 KiB
Python
36 lines
1.3 KiB
Python
import os
|
|
import uuid
|
|
import requests
|
|
from config.logger import setup_logging
|
|
from datetime import datetime
|
|
from core.providers.tts.base import TTSProviderBase
|
|
|
|
TAG = __name__
|
|
logger = setup_logging()
|
|
|
|
class TTSProvider(TTSProviderBase):
|
|
def __init__(self, config, delete_audio_file):
|
|
super().__init__(config, delete_audio_file)
|
|
self.url = config.get("url")
|
|
self.headers = config.get("headers", {})
|
|
self.params = config.get("params")
|
|
self.format = config.get("format", "wav")
|
|
self.output_file = config.get("output_file", "tmp/")
|
|
|
|
def generate_filename(self):
|
|
return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}.{self.format}")
|
|
|
|
async def text_to_speak(self, text, output_file):
|
|
request_params = {}
|
|
for k, v in self.params.items():
|
|
if isinstance(v, str) and "{prompt_text}" in v:
|
|
v = v.replace("{prompt_text}", text)
|
|
request_params[k] = v
|
|
|
|
resp = requests.get(self.url, params=request_params, headers=self.headers)
|
|
if resp.status_code == 200:
|
|
with open(output_file, "wb") as file:
|
|
file.write(resp.content)
|
|
else:
|
|
logger.bind(tag=TAG).error(f"Custom TTS请求失败: {resp.status_code} - {resp.text}")
|