pip install gtts pydub

from gtts import gTTS

# Create speech
tts = gTTS(text="Hello, world!", lang='en')

# Save to file
tts.save("output.mp3")

# US English (default)
tts = gTTS(text="Hello", lang='en')

# British English
tts = gTTS(text="Hello", lang='en', tld='co.uk')

# Slow speech
tts = gTTS(text="Hello", lang='en', slow=True)

from gtts import gTTS
from pydub import AudioSegment
import tempfile
import os
import re

def chunk_text(text, max_chars=4500):
    """Split text into chunks at sentence boundaries."""
    sentences = re.split(r'(?<=[.!?])\s+', text)
    chunks = []
    current_chunk = ""

    for sentence in sentences:
        if len(current_chunk) + len(sentence) < max_chars:
            current_chunk += sentence + " "
        else:
            if current_chunk:
                chunks.append(current_chunk.strip())
            current_chunk = sentence + " "

    if current_chunk:
        chunks.append(current_chunk.strip())

    return chunks


def text_to_audiobook(text, output_path):
    """Convert long text to a single audio file."""
    chunks = chunk_text(text)
    audio_segments = []

    for i, chunk in enumerate(chunks):
        # Create temp file for this chunk
        with tempfile.NamedTemporaryFile(suffix='.mp3', delete=False) as tmp:
            tmp_path = tmp.name

        # Generate speech
        tts = gTTS(text=chunk, lang='en', slow=False)
        tts.save(tmp_path)

        # Load and append
        segment = AudioSegment.from_mp3(tmp_path)
        audio_segments.append(segment)

        # Cleanup
        os.unlink(tmp_path)

    # Concatenate all segments
    combined = audio_segments[0]
    for segment in audio_segments[1:]:
        combined += segment

    # Export
    combined.export(output_path, format="mp3")

# Create file list
echo "file 'chunk1.mp3'" > files.txt
echo "file 'chunk2.mp3'" >> files.txt

# Concatenate
ffmpeg -f concat -safe 0 -i files.txt -c copy output.mp3