Python中edge-tts实现便捷语音合成

pip install edge-tts

import asyncio
import edge_tts

def generate_audio(text: str, voice: str, output_file: str) -> None:
    """
    传入文本、语音及输出文件名，生成语音并保存为音频文件
    :param text: 需要合成的中文文本
    :http://www.chinasem.cnparam voice: 使用的语音类型，如 'zh-CN-XiaoyiNeural'
    :param output_file: 输出的音频文件名
    """
    async def generate_audio_async() -> None:
        """异步生成语音"""
        communicate = edge_tts.Communicate(text, voice)
        await communicate.save(output_file)

    # 异步执行生成音频
    asyncio.run(generate_audio_async())

# 示例调用
generate_audio("今天天气不错，适合出门玩耍。", "zh-CN-XiaoyiNeural", "weather.mp3")

import asyncio
import edge_tts
from edge_tts import VoicesManager

async def print_available_voices(language: str = "zh", gender: str = None) -> None:
    """
    异步查找并打印符合特定条件的语音列表。
    :param language: 语音的语言，如 "zh-CN" 表示中文
    :param gender: 可选参数，选择语音的性别（"Male" 或 "Female"），默认不指定
    """
    # 异步获取所有可用语音
    voices = await VoicesManager.create()

    # 根据语言过滤语音
    filtered_voices = voices.find(Language=language)
    if gender:
        filtered_voices = [voice for voice in filtered_voices if voice["Gender"] == gender]
    
    # 打印符合条件的语音
    if filtered_voices:
        print(f"符合条件的语音：China编程")
        for voice in filtered_voices:
            print(f"语音名称: {voice['Name']}, 性别: {voice['Gender']}, 语言: {voice['Language']}")
    else:
        print(f"没有找到符合条件的语音：语言={language}, 性别={gender}")

# 示例调用
async def main():
    await print_available_voices(language="zh", gender="Female")

# 运行异步示例
if __name__ == "__main__":
    asyncio.run(main())

import edge_tts

def generate_audio_with_custom_params(text: str, output_file: str, rate: str = "+0%", pChina编程itch: str = "+0Hz", volume: str = "+0%") -> None:
    """
    生成带有自定义语音参数的音频
    :param text: 需要合成的中文文本
    :param output_file: 输出的音频文件名
    :param rate: 语速调整（默认为 "+0%"，表示标准语速）
    :param pitch: 音调调整（默认为 "+0Hz"，表示标准音调）
    :param volume: 音量调整（默认为 "+0%"，表示标准音量）
    """
    # 选择中文语音，这里使用的是小艺的 Neural 语音
    voice = "zh-CN-XiaoyiNeural"  
    
    # 使用 edge_tts.Communicate 创建语音对象，并传入自定义参数
    communicate = edge_tts.Communicate(text, voice, rate=rate, pitch=pitch, volume=volume)
    
    # 保存生成的音频文件
    communicate.save_sync(output_file)
    print(f"音频已生成，语速: {rate}，音调: {pitch}，音量: {volume}。")

# 示例调用
generate_audio_with_custom_params(
    "欢迎体验自定义语音合成！", 
    "custom_param_audio.wav", 
    rate="+50%", 
    pitch="+10Hz", 
    volume="-20%"
)

import asyncio
import edge_tts

def process_audio_and_subtitles_sync(text: str, voice: str, output_file: str, srt_file: str) -> None:
    """
    同步生成音频并实时生成字幕
    :param text: 需要合成的中文文本
    :param voice: 使用的语音类型
    :param output_file: 输出的音频文件名
    :param srt_file: 输出的字幕文件名
    """
    communicate = edge_tts.Communicate(text, voice)
    submaker = edge_tts.SubMaker()

    # 同步生成音频并实时生成字幕
    with open(output_file, "wb") as audio_file:
        for chunk in communicate.stream_sync():
            if chunk["type"] == "audio":
                audio_file.write(chunk["data"])  # 写入音频数据
            elif chunk["type"] == "WordBoundary":
                submaker.feed(chunk)  # 处理字幕

    # 保存字幕文件
    with open(srt_file, "w", encoding="utf-8") as subtitle_file:
        subtitle_file.write(submaker.get_srt())

async def process_audio_and_subtitles_async(text: str, voice: str, output_file: str, srt_file: str) -> None:
    """
    异步生成音频并实时生成字幕
    :param text: 需要合成的中文文本
    :param voice: 使用的语音类型
    :param output_file: 输出的音频文件名
    :param srt_file: 输出的字幕文件名
    """
    # 异步调用同步版本的逻辑
    loop = asyncio.get_event_loop()
    await loop.run_in_executor(None, process_audio_and_subtitles_sync, text, voice, output_file, srt_file)

# 示例调用
process_audio_and_subtitles_s编程ync("欢迎使用 Python 进行语音合成！", "zh-CN-XiaoyiNeural", "audio_sync.mp3", "audio_sync.srt")

# 异步调用
asyncio.run(process_audio_and_subtitles_async("这是一段测试语音和字幕生成的示例。", "zh-CN-XiaoyiNeural", "audio_async.mp3", "audio_async.srt"))