python文本转音频模块的调用示例--确保文本不要太长

原创

于 2025-06-01 16:25:38 发布 · 103 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #音视频 #开发语言

from gtts import gTTS
from pydub import AudioSegment
from pydub.playback import play as pydub_play  # 使用 pydub 的播放方法
import os
import time

# 设置环境变量以确保 pydub 可以找到 ffmpeg
os.environ["PATH"] += os.pathsep + r'E:\ffmpeg-master-latest-win64-gpl-shared\bin'

def speed_up_audio(file_path, speed=1.25):
    sound = AudioSegment.from_file(file_path)
    sound_with_altered_frame_rate = sound._spawn(sound.raw_data, overrides={
        "frame_rate": int(sound.frame_rate * speed)
    })
    adjusted_audio_file = "temp_adjusted_output.mp3"
    sound_with_altered_frame_rate.export(adjusted_audio_file, format="mp3")
    return adjusted_audio_file

def text_to_speech(text, lang='zh', speed=1.25):
    tts = gTTS(text=text, lang=lang, slow=False)
    original_audio_file = "temp_output.mp3"

    try:
        tts.save(original_audio_file)
        print("原始语音文件已生成")

        if speed != 1.0:
            adjusted_audio_file = speed_up_audio(original_audio_file, speed=speed)