ElevenLabs Speech Engine

Your runtime, their STT/TTS. Cloud + key. Not LiveKit OSS

ElevenLabs · MIT

When

Real-time voice on a custom agent runtime via ElevenLabs Speech Engine (WebSocket, WebRTC, conversation tokens). They handle mic/STT/turn-taking/TTS; your server owns agent logic. Needs API key. Not LiveKit Agents OSS. Not the TTS-only skill.

The Catch

Your runtime, their STT/TTS. Cloud + API key, not LiveKit OSS. Free has no commercial license. Distinct from elevenlabs-text-to-speech.

Embed

[![Reviewed on Stack Gems](https://stackgems.com/badge/skill/elevenlabs-speech-engine.svg)](https://stackgems.com/skills/elevenlabs-speech-engine)