This repository offers a collection of AI agent skills designed to integrate ElevenLabs' advanced audio and voice technologies into developer workflows and AI coding assistants. It empowers developers to easily add features like lifelike text-to-speech, speech-to-text transcription, real-time voice conversations, sound effect generation, and AI music composition to their applications. The skills abstract complex API interactions, streamlining the development of voice-enabled AI experiences.

How It Works

The project provides a modular set of "skills" that adhere to the Agent Skills specification, making them compatible with various AI coding assistants. Each skill encapsulates a specific ElevenLabs API functionality, such as converting text to speech or generating sound effects from text descriptions. This approach allows developers to discover, add, and utilize these powerful audio AI capabilities directly within their development environment or custom AI agents without needing to manage low-level API calls.

Quick Start & Requirements

• Primary install / run command: npx skills add elevenlabs/skills
• Non-default prerequisites and dependencies: An ElevenLabs API key is mandatory, configurable via the ELEVENLABS_API_KEY environment variable. SDKs are available for Python (pip install elevenlabs) and JavaScript/TypeScript (npm install @elevenlabs/elevenlabs-js). Note: Use the @elevenlabs/elevenlabs-js package, not the outdated npm install elevenlabs.
• Evaluations: The evals/ directory contains scripts (python3 evals/run_all.py) for running trigger and functional tests, requiring the Cursor Agent CLI (cursor-agent) to be installed and authenticated.

Highlighted Details

• Comprehensive suite of audio AI skills including text-to-speech, speech-to-text, voice changing, sound effects, and AI music generation.
• Designed for integration with AI coding assistants following the Agent Skills specification.
• Includes detailed evaluation scripts for testing skill functionality and triggers.
• Provides official SDKs for Python and JavaScript/TypeScript for easier integration.

Maintenance & Community

The provided README does not contain specific details regarding notable contributors, sponsorships, community channels (like Discord/Slack), or a public roadmap.

Licensing & Compatibility

The project is released under the MIT license, which generally permits broad use, modification, and distribution, including for commercial purposes, with minimal restrictions beyond attribution.

Limitations & Caveats

The primary dependency for running evaluations is the Cursor Agent CLI, which may not be universally available or desired by all users. The README also explicitly warns against using an outdated JavaScript package (npm install elevenlabs), requiring careful attention to SDK versioning.