Project

Elevenlabs

Build voice-enabled AI agents with real-time speech-to-text, LLM, and natural text-to-speech orchestration.

Readme
↓  Open

The ElevenLabs Agents Platform allows you to build voice-enabled AI agents with real-time speech-to-text, LLM, and natural text-to-speech orchestration -- powered by industry-leading voice AI technology. All participants receive 3 months of Creator Plan access for the hackathon, with 750 minutes of conversations included.

👉 Agents Platform Quickstart | API Documentation

How to Get Started

  • Find your an access link for your Creator Plan access in your personal profile

  • Include your team name and project description

  • Each participant receives 3 months of Creator Plan access

  • Access includes all Agents Platform features plus TTS and Music APIs

  • Do NOT share access credentials across teams to prevent rate limiting issues

  • Test your agent using our Dashboard

Included: Agents Platform

  • Real-time Speech-to-Text - Low-latency voice recognition in 29+ languages
  • LLM Orchestration - Seamless integration with GPT-4, Claude, and custom models
  • Text-to-Speech - Natural voices with <500ms latency
  • WebSocket and WebRTC Support - For real-time bidirectional streaming
  • Knowledge Base - Equip agents with documents and external resources
  • Custom Tools - Extend agent capabilities with custom API integrations and MCP server support
  • Analytics Dashboard - Monitor conversations and agent performance

Included: Additional APIs

ElevenLabs Examples

This collection of demos and projects showcases the ElevenLabs API and how you can start building next generation AI audio apps with it. Whether you're looking to integrate text-to-speech into your website, create dubbed content, or explore advanced conversational applications, you'll find valuable resources here.

🚀 Featured Projects

Conversational AI Demos

These projects offer practical examples of building real-time, voice-driven applications with rich interactivity.

Text-to-Speech (TTS) Demos

  • Standard TTS Demo: A straightforward implementation of our core TTS functionality.
  • TTS WebSocket Demo with Latency Measurement: Explore real-time text-to-speech with performance metrics.

Native Mac App (Open Source)

A fully open-source native Mac application that brings ElevenLabs to your desktop. Written by Claude 3.5 and Cursor.

Sound Effects Generation

Unleash your creativity with our sound effects generation demo. Create custom audio landscapes for your projects!

AudioNative React Demo

Embed ElevenLabs' text-to-speech capabilities directly into your React-based websites. This demo shows you how to seamlessly integrate our technology for a native-like audio experience.

Dubbing API Demo

Discover how to use our Dubbing API to create multilingual content effortlessly. Perfect for content creators and localization teams!

Pronunciation Dictionaries

Learn how to work with pronunciation dictionaries to fine-tune the output of our voice models.

🛠 Getting Started

To get started with these examples:

  1. Clone this repository
  2. Navigate to the project you're interested in
  3. Follow the project-specific README for setup instructions

For detailed API documentation and guides, visit our Developer Docs.

🤝 Contributing

We welcome contributions from the community! Before you start:

  1. Install the pre-commit hook:
    pip install pre-commit
pre-commit install
  2. Check out our Contributing Guidelines for more information on how to submit pull requests, report issues, and suggest improvements.

📚 Learn More

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

👋 Contact 💻 Source

Previous
Return
Next project