文字转语音 edge_tts

发布于:2025-08-16 ⋅ 阅读:(19) ⋅ 点赞:(0)

1、前沿

这是一款微软语音转文字的项目,不要电脑配置因为他是通过类爬虫方式把文字转语音,跟官方比起来速度会慢一点但是基本够用

https://github.com/rany2/edge-tts

2、代码封装

默认是通过命令行的方式不适合集成到我们自己的项目通过封装成接口的方式使用

@router.get("/text-to-speech", tags=["语音合成"], summary="文字转语音")
async def text_to_speech(text: str):
    try:
        file_path = await edge_tts_async(text)
        return FileResponse(
            path=file_path, media_type="audio/mp3", filename=os.path.basename(file_path)
        )
    except Exception as e:
        return {"error": f"转换失败: {str(e)}"}


import edge_tts

async def edge_tts_async(text):
    num = random.randint(1, 100000000)
    static_dir = "static/audio"
    os.makedirs(static_dir, exist_ok=True)
    file_path = os.path.join(static_dir, f"{num}.mp3")

    # 从配置获取代理设置(如果有)
    proxy = None
    if "proxies" in GLOBAL_CONFIG and "proxy" in GLOBAL_CONFIG["proxies"]:
        proxy = GLOBAL_CONFIG["proxies"]["proxy"]
    
    try:
        # 使用edge_tts.Communicate类进行文字转语音
        communicate = edge_tts.Communicate(
            text,
            "zh-CN-XiaoyiNeural",
            proxy=proxy,
            connect_timeout=20,
            receive_timeout=60
        )
        
        # 保存音频文件
        await communicate.save(file_path)
        return file_path
    except Exception as e:
        log_error(f"文字转语音失败: {str(e)}")
        raise Exception(f"TTS conversion failed: {str(e)}")