audio-mcp

three.ws Audio

Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.

stdioofficialservice

Package Details

@three-ws/audio-mcp

0.1.0•https://www.npmjs.com/package/@three-ws/audio-mcp

Transportstdio

Runtimenpx

Environment Variables

THREE_WS_BASE(str)

Default:https://three.ws

Base URL of the three.ws API that serves the audio/animation endpoints. Override only when self-hosting or targeting a preview deployment.

THREE_WS_API_KEY(str)

Secret

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.

THREE_WS_TIMEOUT_MS(num)

Default:60000

Per-request timeout in milliseconds for the live audio/animation calls (synthesis and recognition are real upstream model calls).