three.ws Audio MCP server
Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
206 stars38 downloads/wk
Reviews
Write oneNobody has reviewed three.ws Audio yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
three.ws Audio tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-22 · same rubric, same numbers if you re-run it
- Code scan10 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
What the publisher says
From the three.ws Audio repository's README, as published. We do not edit it. Read it on GitHub
three.ws
Website · Docs · Changelog · X / Twitter · GitHub · $THREE on pump.fun
https://github.com/user-attachments/assets/d52515d1-cb04-4dd6-98bd-fef233312dc4
Give your AI a body. three.ws is an open source (Apache-2.0), browser-native 3D AI agent platform. Type a prompt and Forge generates a textured 3D model, or drop a GLB you already have. Add an LLM brain, register on-chain, and embed anywhere: no plugins, no server uploads, no installs required.
Try it in 60 seconds: open three.ws/forge, type "a brass steampunk owl, full body", and download the GLB. Text→3D, image→3D, and sketch→3D — free draft tier, no account. Jump to the Forge section ↓
Want to build it with us? Your first contribution goes from clone to open pull request in about 15 minutes, with a full worked example. Every good first issue names the file to change and the command that proves it worked. Say hello in Discussions or Telegram.
Meet the avatar: a live 3D model, right here in markdown
Drag to rotate. This is not an image or a video: it is an interactive 3D model rendered natively by GitHub. The avatar was generated from a one-line text prompt on three.ws Forge (free tier), decimated to 1,200 triangles, and embedded as ASCII STL with readme-3d, our open-source toolkit for putting 3D models in any GitHub README, issue, or discussion.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
Runs npx -y @three-ws/audio-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add audio-mcp -- npx -y @three-ws/audio-mcp
three.ws Audio: common questions
- Is three.ws Audio MCP server safe?
- Mostly: it is graded B (83/100). Read the three.ws Audio safety report
- How do I install three.ws Audio?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does three.ws Audio need an API key?
- Yes. The registry entry asks for
THREE_WS_API_KEY. - Is three.ws Audio maintained?
- The last commit was in the last day (2026-09-22). The latest release is v0.1.2.
- What can I use instead of three.ws Audio?
- Servers from other publishers that do the same job: Fish MCP server, Vidofy MCP server and Justtranscribe MCP server. Compare all three.ws Audio alternatives.
Alternatives to three.ws Audio
Same job from other publishers: the closest match first, then the best rated.
- FishMCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning)not reviewedGrowingA
- VidofyGenerate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.not reviewedGrowingA
- JusttranscribeTranscribe public videos & audio (YouTube, TikTok, IG) into accurate, timestamped text via API.not reviewedGrowingA
- OllosLocal, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.not reviewedGrowingA
- NotebookLM MCPAutomate Google NotebookLM — Q&A with citations, audio, video, content generationnot reviewedEstablishedC
