Build an original project that uses ElevenLabs AI voice, audio, or speech technologies as a core component of how it works. Teams could integrate high-fidelity text-to-speech (TTS), speech-to-speech voice conversion, real-time Conversational AI agents, custom voice cloning, or automated dubbing and sound generation. These are examples within one challenge, and teams may combine them.

ElevenLabs Integration: ElevenLabs API, SDKs, or tools must play a central role in the project’s user experience or backend workflow.

Open Source & Licensing: The project must be published in a public GitHub repository and use an open-source license.

Conversational & Interactive Features: If using ElevenLabs Conversational AI or Agent features, the integration must demonstrate dynamic, interactive voice capabilities or custom tool usage.

Audio & Media Applications: Submissions using voice cloning, dubbing, or sound effects must include an original implementation, workflow, or interactive application around the generated audio.