Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

three.ws Audio

NPM · @THREE-WS/AUDIO-MCP · SCANNED AUG 3

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

Available components

+24 this week 66 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability63
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1573 tokens (~314/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @three-ws/audio-mcp

# add to Claude Code
claude mcp add nirholas-audio-mcp -- npx -y @three-ws/audio-mcp
# add to Codex CLI
codex mcp add nirholas-audio-mcp -- npx -y @three-ws/audio-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nirholas-audio-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@three-ws/audio-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add nirholas-audio-mcp --command npx --arg -y --arg @three-ws/audio-mcp
# ~/.hermes/config.yaml
mcp_servers:
  nirholas-audio-mcp:
    command: "npx"
    args: ["-y", "@three-ws/audio-mcp"]
// mcp.json
{
  "mcpServers": {
    "nirholas-audio-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@three-ws/audio-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +3
    • Stability: unverified → 0.23 functional
  • 2 Aug 26 +46
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Schema quality: unverified → excellent functional
    • Licence: Apache-2.0 functional
  • 31 Jul 26 −7
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 42

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@three-ws/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 5 exposed · ~1,369 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
audio_to_face ~363

Generate a per-frame ARKit blendshape lipsync track from speech using free NVIDIA NIM Audio2Face-3D. Provide either `text` (the server synthesizes it with Magpie TTS, then animates that clip and returns both the audio and the animation) or `audio` (base64 wav/pcm you already have, so the lips match the exact bytes you will play). Returns { animation: { fps, blendShapeNames, frames, durationSec } } where each frame is { t, w } — t in seconds, w = weights ordered by blendShapeNames (ARKit-52). On the text path it also returns { audio: { base64, contentType, format } }. Read-only — produces an animation track without changing platform state.

NameTypeReqDescription
audiostringPre-synthesized audio to animate, base64-encoded (raw or a data: URL). Provide this OR `text`. Set `format` to match the bytes.
formatstringEncoding of `audio` (default "wav"). Use "pcm" for raw 16-bit little-endian PCM and set `sampleRate`.
languagestringBCP-47 language for the text path (default "en-US"). Ignored when `audio` is supplied.
sampleRateintegerSample rate in Hz for raw PCM `audio` (default 16000). Ignored for WAV.
textstringText to synthesize and animate (1–4096 chars). Provide this OR `audio`. On this path the synthesized audio is returned alongside the animation.
voicestringVoice for the text path (default "nova"). Ignored when `audio` is supplied.

No output schema declared.

No examples provided.

motion_capture_clip ~147

Fetch a single motion-capture clip by id, including its full per-frame animation track. Returns { clip } with metadata plus `frames`: each frame is { t, shapes, mat? } — t in seconds, shapes a name→weight map (ARKit blendshapes for face clips; joint channels for pose/hand/vmc), and an optional 16-float transform matrix. Use this to drive an avatar from a clip discovered via motion_capture_clips. Public and unlisted clips are readable anonymously; a private clip needs THREE_WS_API_KEY for its owner. Read-only.

NameTypeReqDescription
idstringyesThe clip id (UUID) returned by motion_capture_clips.

No output schema declared.

No examples provided.

motion_capture_clips ~221

List motion-capture clips from the three.ws library — recorded face/pose/hand/VMC tracks an avatar can play back. Returns clip metadata (id, slug, name, kind, format, duration_ms, frame_count, tags, visibility, play_count, price) but NOT the frames; fetch a clip by id with motion_capture_clip to get the animation track. Anonymous callers see only public clips; set THREE_WS_API_KEY to include your own. Cursor-paginated via next_cursor. Read-only live data.

NameTypeReqDescription
cursorstringPagination cursor from a previous response's next_cursor.
include_publicbooleanWhen authenticated (THREE_WS_API_KEY set), return your clips AND public ones instead of just your own. Ignored anonymously (always public-only).
kindstringFilter by capture kind: "face" (blendshapes), "pose" (body), "hand", or "vmc".
limitintegerHow many clips to return (1–100, default 50).

No output schema declared.

No examples provided.

speech_to_text ~294

Transcribe spoken audio to text using the free NVIDIA NIM Riva recognizer. Pass the audio as base64 (raw or a data: URL). Accepted encodings: wav, pcm (set sampleRate), flac, ogg/opus — the WebM container from a browser MediaRecorder must be decoded to WAV or PCM first. Returns { text, confidence, language, model, durationSec } and, when `words` is set, per-word timestamps. Audio is capped at ~8 MB. Read-only — recognizes speech without changing any platform state.

NameTypeReqDescription
audiostringyesThe audio to transcribe, base64-encoded (a raw base64 string or a data:<mime>;base64,… URL). Max ~8 MB decoded.
formatstringAudio encoding of the supplied bytes (default "wav"). Use "pcm" for raw 16-bit little-endian PCM (set sampleRate).
languagestringBCP-47 language hint for recognition (default "en-US").
modelstringOverride the Riva model name (advanced; defaults to the configured model).
sampleRateintegerSample rate in Hz for raw PCM input (default 16000). Ignored for WAV, which carries its own rate in the header.
wordsbooleanWhen true, also return per-word timestamps in a `words` array.

No output schema declared.

No examples provided.

text_to_speech ~344

Synthesize spoken audio from text for a 3D avatar and return it as a base64 audio data URL (data:<mime>;base64,…) plus metadata. Free NVIDIA NIM Magpie TTS leads; OpenAI is the paid backstop. Because Magpie emits raw PCM, every non-pcm request is served as WAV — the returned `mime`, `format`, and `voice` describe the bytes you actually get, not the request. Pair the audio with audio_to_face to drive lipsync. Input text is capped at 4096 characters. Read-only — synthesizes audio without changing any platform state.

NameTypeReqDescription
formatstringRequested audio container (default "mp3"). The free NVIDIA lane serves every non-pcm request as WAV; the response metadata reports what you actually received.
languagestringBCP-47 language for the free NVIDIA lane (default "en-US"; also es-US, fr-FR, de-DE, zh-CN, vi-VN, it-IT, hi-IN, ja-JP).
modelstringOpenAI TTS model for the paid backstop lane (default "gpt-4o-mini-tts"). Ignored by the free NVIDIA lane, which always uses magpie-tts-multilingual.
speednumberPlayback speed multiplier, 0.5–2.0 (OpenAI backstop lane only; default 1.0).
textstringyesThe text to speak (1–4096 characters).
voicestringVoice persona (default "nova"). The same id renders on either provider lane.

No output schema declared.

No examples provided.