Package
three.ws Audio
Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
io.github.nirholas/audio-mcpSource repository
Overview
What this server provides
Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
Install
1Packages
@three-ws/audio-mcp0.1.3
Runtime
npxTransport stdio- THREE_WS_BASEOptional
Base URL of the three.ws API that serves the audio/animation endpoints. Override only when self-hosting or targeting a preview deployment.
Format: string · Default: https://three.ws - THREE_WS_API_KEYOptional
Optional three.ws API key (bearer token). Raises the metered TTS/ASR/Audio2Face rate limits and unlocks your own private/unlisted motion-capture clips. Leave unset to use the public surface anonymously.
Format: string - THREE_WS_TIMEOUT_MSOptional
Per-request timeout in milliseconds for the live audio/animation calls (synthesis and recognition are real upstream model calls).
Format: number · Default: 60000