gtts

1# Google Text-to-Speech (gTTS)
2 
3gTTS is a Python library that converts text to speech using Google's Text-to-Speech API. It's free to use and doesn't require an API key.
4 
5## Installation
6 
7```bash
8pip install gtts pydub
9```
10 
11pydub is useful for manipulating and concatenating audio files.
12 
13## Basic Usage
14 
15```python
16from gtts import gTTS
17 
18# Create speech
19tts = gTTS(text="Hello, world!", lang='en')
20 
21# Save to file
22tts.save("output.mp3")
23```
24 
25## Language Options
26 
27```python
28# US English (default)
29tts = gTTS(text="Hello", lang='en')
30 
31# British English
32tts = gTTS(text="Hello", lang='en', tld='co.uk')
33 
34# Slow speech
35tts = gTTS(text="Hello", lang='en', slow=True)
36```
37 
38## Python Example for Long Text
39 
40```python
41from gtts import gTTS
42from pydub import AudioSegment
43import tempfile
44import os
45import re
46 
47def chunk_text(text, max_chars=4500):
48    """Split text into chunks at sentence boundaries."""
49    sentences = re.split(r'(?<=[.!?])\s+', text)
50    chunks = []
51    current_chunk = ""
52 
53    for sentence in sentences:
54        if len(current_chunk) + len(sentence) < max_chars:
55            current_chunk += sentence + " "
56        else:
57            if current_chunk:
58                chunks.append(current_chunk.strip())
59            current_chunk = sentence + " "
60 
61    if current_chunk:
62        chunks.append(current_chunk.strip())
63 
64    return chunks
65 
66 
67def text_to_audiobook(text, output_path):
68    """Convert long text to a single audio file."""
69    chunks = chunk_text(text)
70    audio_segments = []
71…