What is ElevenLabs?
ElevenLabs is a leading AI voice platform that provides:- Text-to-Speech: Convert text into natural-sounding speech in 70+ languages
- Voice Cloning: Create custom voice clones from audio samples
- Speech-to-Text: Transcribe audio with high accuracy
- Conversational AI: Build interactive AI agents with real-time audio capabilities
- Voice Library: Access thousands of pre-made voices or create your own
Get Started
Quickstart
Generate your first text-to-speech audio in minutes
Installation
Install the SDK and set up your development environment
Authentication
Configure your API key and client settings
API Reference
Explore the complete API documentation
Key Features
Multiple AI Models
Choose from powerful models optimized for different use cases:- Eleven v3 - Dramatic performances with 70+ languages
- Eleven Multilingual v2 - Superior stability and accent accuracy in 29 languages
- Eleven Flash v2.5 - Ultra-low latency, 50% lower cost
- Eleven Turbo v2.5 - Optimal balance of quality and speed
Streaming Support
Stream audio in real-time as it’s being generated for responsive user experiences.Async Client
Full async/await support withAsyncElevenLabs for high-performance applications.
Voice Customization
Fine-tune voice settings, clone voices, and access a library of pre-made voices.SDK Information
- Package Name:
elevenlabs - Current Version: v2.37.0
- Python Support: 3.8, 3.9, 3.10, 3.11, 3.12
- License: MIT
- Repository: GitHub
Community & Support
Discord Community
Join our Discord server for help and discussions
Follow us for updates and announcements