75 lines
2.2 KiB
Python
75 lines
2.2 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""
|
||
合成语音模块
|
||
"""
|
||
|
||
import asyncio
|
||
from hashlib import md5
|
||
from pathlib import Path
|
||
from typing import Tuple, Union
|
||
|
||
import edge_tts
|
||
from mutagen.mp3 import MP3
|
||
|
||
|
||
# pylint: disable=too-few-public-methods
|
||
class EdgeTTS:
|
||
"""
|
||
EdgeTTS模块，支持：
|
||
1、根据文本合成语音并将语音文件保存至指定文件夹内
|
||
"""
|
||
|
||
def __init__(
|
||
self,
|
||
folder_path: Union[str, Path],
|
||
):
|
||
"""
|
||
初始化
|
||
:param folder_path: 语音文件保存文件夹路径
|
||
"""
|
||
# 指定文件夹路径（path对象）
|
||
self.folder_path = (
|
||
folder_path if isinstance(folder_path, Path) else Path(folder_path)
|
||
)
|
||
|
||
def synthetize(
|
||
self,
|
||
text: str,
|
||
timbre: str,
|
||
rate: str,
|
||
volume: str,
|
||
) -> Tuple[Path, int]:
|
||
"""
|
||
根据文本合成语音并将语音文件保存至指定文件夹内
|
||
:param text: 文本
|
||
:param timbre: 音色名称
|
||
:param rate: 语速
|
||
:param volume: 音量
|
||
:return: 语音文件路径（path对象）和持续时长（单位为微秒）
|
||
"""
|
||
try:
|
||
# 异步处理方法
|
||
async def _async_synthetize():
|
||
# 构造语音文件名称
|
||
file_name = f"{md5((text + timbre + rate + volume).encode("utf-8"))
|
||
.hexdigest()
|
||
.upper()}.mp3"
|
||
# 构造语音文件路径
|
||
file_path = self.folder_path / file_name
|
||
communicator = edge_tts.Communicate(
|
||
text=text.replace("\n", ""),
|
||
voice=timbre,
|
||
rate=rate,
|
||
volume=volume,
|
||
)
|
||
await communicator.save(file_path.as_posix())
|
||
# 持续时长（单位为微秒）
|
||
duration = int(round(MP3(file_path.as_posix()).info.length * 1000000))
|
||
return file_path, duration
|
||
|
||
return asyncio.run(_async_synthetize())
|
||
except Exception as exception:
|
||
raise RuntimeError(
|
||
f"根据文本合成语音并将语音文件保存至指定文件夹内发生异常：{str(exception)}"
|
||
) from exception
|