ToolsMCP
three.ws Audio
Listed in the official MCP Registry with an installable npm package. Capabilities below are the publisher’s own description.
- Type
- MCP server
- Publisher
- nirholas (GitHub)
- Prerequisites
- Install @three-ws/audio-mcp from npm (stdio transport). Declares 1 secret input. Inspect it before installing; AgentsByTask never installs discovered packages.
- Current version
- 0.1.3 · updated
- Official links
Publisher’s description
Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
Evidence
Each record keeps its own date and scope. Labels are independent: documentation does not imply a checked connection, and a connection does not imply a passed task.
-
Listed in the official MCP Registry
Version 0.1.3, registry status active. 1 package (npm)
Publisher-supplied registry metadata. Not a checked connection, a safe package or a completed task.
- Source publisher
- nirholas (GitHub)
- Version observed
- 0.1.3
- Source
- registry.modelcontextprotocol.io/v0.1/servers/io.github.nirholas%2Faudio-mcp/versions/0.1.3
Listed for these tasks
| Task | Documented for this task | Unknowns | Why it is listed |
|---|---|---|---|
| Transcribe audio and meetings | Publisher description mentions “speech-to-text”, “audio”. | No connection check or task run. Capability is as described by the publisher. | Rule transcription matched: “speech-to-text”, “audio”. Rule transcription. |
Published pricing
No published price recordedCost per completed task is only shown on a task page when a comparable run recorded metered spend and verified completions.
Registry record
- Packages
@three-ws/audio-mcp(npm, stdio, 1 secret input)- Registry entry
- Official MCP Registry record (JSON)
- Namespace
io.github.nirholas/audio-mcp
AgentsByTask never installs discovered packages or connects to discovered endpoints during discovery. An endpoint string in a registry record is not a checked connection.