mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-22 15:13:55 +08:00
46 lines
1.8 KiB
Python
46 lines
1.8 KiB
Python
import os
|
|
import uuid
|
|
import edge_tts
|
|
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)
|
|
if config.get("private_voice"):
|
|
self.voice = config.get("private_voice")
|
|
else:
|
|
self.voice = config.get("voice")
|
|
self.audio_file_type = config.get("format", "mp3")
|
|
|
|
def generate_filename(self, extension=".mp3"):
|
|
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):
|
|
try:
|
|
communicate = edge_tts.Communicate(text, voice=self.voice)
|
|
if output_file:
|
|
# 确保目录存在并创建空文件
|
|
os.makedirs(os.path.dirname(output_file), exist_ok=True)
|
|
with open(output_file, "wb") as f:
|
|
pass
|
|
|
|
# 流式写入音频数据
|
|
with open(output_file, "ab") as f: # 改为追加模式避免覆盖
|
|
async for chunk in communicate.stream():
|
|
if chunk["type"] == "audio": # 只处理音频数据块
|
|
f.write(chunk["data"])
|
|
else:
|
|
# 返回音频二进制数据
|
|
audio_bytes = b""
|
|
async for chunk in communicate.stream():
|
|
if chunk["type"] == "audio":
|
|
audio_bytes += chunk["data"]
|
|
return audio_bytes
|
|
except Exception as e:
|
|
error_msg = f"Edge TTS请求失败: {e}"
|
|
raise Exception(error_msg) # 抛出异常，让调用方捕获 |