Audiobook Generator

Generate high-quality audiobooks from text or text files using the Eleven Labs API.

Features

• Convert text directly to audio
• Convert text files to audiobooks
• Support for multiple voice options
• Easy-to-use command-line interface
• Python API for programmatic usage

Prerequisites

• Python 3.7 or higher
• Eleven Labs API key (get one at https://elevenlabs.io)

Installation

1. Clone this repository:

git clone <your-repo-url>
cd hello-world

2. Install dependencies:

pip install -r requirements.txt

3. Set up your API key:

cp .env.example .env

Edit .env and add your Eleven Labs API key:

ELEVENLABS_API_KEY=your_api_key_here

Usage

Command Line Interface

Generate audiobook from text:

python audiobook_generator.py --text "Your text here" --output my_audiobook.mp3

Generate audiobook from a file:

python audiobook_generator.py --file example.txt --output example.mp3

List available voices:

python audiobook_generator.py --list-voices

Use a specific voice:

python audiobook_generator.py --file example.txt --voice <voice-id> --output custom_voice.mp3

Python API

from audiobook_generator import AudiobookGenerator

# Initialize generator
generator = AudiobookGenerator()

# Generate from text
generator.generate_audiobook(
    text="Your text content here",
    output_path="output.mp3"
)

# Generate from file
generator.generate_from_file(
    input_file="book.txt",
    output_path="audiobook.mp3"
)

# List available voices
generator.list_voices()

Examples

Check out usage_examples.py for more detailed examples including:

• Direct text to audio conversion
• File to audio conversion
• Using custom voices
• Batch processing multiple files

Run the example:

python audiobook_generator.py --file example.txt

Configuration

You can configure the following options in your .env file:

• ELEVENLABS_API_KEY: Your Eleven Labs API key (required)
• DEFAULT_VOICE_ID: Default voice ID to use (optional, defaults to Rachel)

Available Models

• eleven_monolingual_v1: English-only model (default)
• eleven_multilingual_v1: Supports multiple languages
• eleven_turbo_v2: Faster generation with good quality

Specify model with --model flag:

python audiobook_generator.py --file text.txt --model eleven_turbo_v2

Output

Generated audiobooks are saved as MP3 files. The output location can be:

• Specified with --output flag
• Auto-generated based on input filename
• Placed in output/ directory for programmatic usage

Troubleshooting

API Key Error: Make sure your .env file contains a valid ELEVENLABS_API_KEY

File Not Found: Ensure the input file path is correct and the file exists

Voice ID Error: List available voices with --list-voices and use a valid voice ID

API Rate Limits

Be aware of Eleven Labs API rate limits and quotas for your subscription tier. Check your usage at https://elevenlabs.io/app/usage

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.