📦 gtts — 文本转语音

Use the gTTS (Google Text-to-Speech) Python library to convert text to audio.

When to use this skill

• Converting text to spoken audio (e.g., for audiobooks, podcasts)
• Speech synthesis from text input
• Handling long text by chunking and concatenating audio

Installation

pip install gtts pydub

Optionally, install ffmpeg for audio concatenation:

# Ubuntu/Debian
sudo apt-get install ffmpeg
# macOS
brew install ffmpeg
# Windows
# Download from https://ffmpeg.org/download.html

Usage

Basic usage

from gtts import gTTS
text = "Hello, this is a test."
tts = gTTS(text=text, lang='en')
tts.save("output.mp3")

Handling long text

For long text, chunk it and concatenate the audio files:

import os
from gtts import gTTS
from pydub import AudioSegment
from pydub.playback import play
def text_to_audio(text, lang='en', chunk_size=1000):
    """Convert long text to audio by chunking."""
    # Split text into chunks
    chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
    
    temp_files = []
    for i, chunk in enumerate(chunks):
        tts = gTTS(text=chunk, lang=lang)
        temp_file = f"temp_chunk_{i}.mp3"
        tts.save(temp_file)
        temp_files.append(temp_file)
    
    # Concatenate audio files
    combined = AudioSegment.empty()
    for file in temp_files:
        combined += AudioSegment.from_mp3(file)
    
    combined.export("output.mp3", format="mp3")
    
    # Cleanup
    for file in temp_files:
        os.remove(file)
# Usage
long_text = "Your long text here..."
text_to_audio(long_text, lang='en')

Using ffmpeg for concatenation

import os
import subprocess
from gtts import gTTS
def text_to_audio_ffmpeg(text, lang='en', chunk_size=1000):
    """Convert long text to audio using ffmpeg for concatenation."""
    chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
    
    temp_files = []
    for i, chunk in enumerate(chunks):
        tts = gTTS(text=chunk, lang=lang)
        temp_file = f"temp_chunk_{i}.mp3"
        tts.save(temp_file)
        temp_files.append(temp_file)
    
    # Create file list for ffmpeg
    with open("file_list.txt", "w") as f:
        for file in temp_files:
            f.write(f"file '{file}'\n")
    
    # Concatenate using ffmpeg
    subprocess.run([
        "ffmpeg", "-f", "concat", "-safe", "0",
        "-i", "file_list.txt", "-c", "copy", "output.mp3"
    ])
    
    # Cleanup
    for file in temp_files:
        os.remove(file)
    os.remove("file_list.txt")
# Usage
long_text = "Your long text here..."
text_to_audio_ffmpeg(long_text, lang='en')

Notes

• gTTS sends text to Google's public TTS endpoints
• Avoid sending sensitive or confidential information
• gTTS is different from Google Cloud Text-to-Speech (no API key required)
• May be rate-limited or subject to service changes
• For production use, consider Google Cloud Text-to-Speech API