What it does
The server exposes Speechmatics speech-to-text to any MCP-compatible client, including Claude. It lets an assistant transcribe audio and video files as part of a conversation or workflow, so the transcription step does not have to be run separately.
It suits cases where a user wants to turn recordings or video soundtracks into text from inside an AI client, for example to review a meeting, interview or media clip without leaving the chat. The publisher's description covers transcription only; no other capabilities are listed.
Running it requires registering the server with an MCP client and supplying the credentials that the Speechmatics service needs. The source does not describe the exact setup steps.
Limitations and requirements
Use of the Speechmatics service requires a Speechmatics account and API access, which the publisher's material indicates but does not detail.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 16 Nov 2026 · its page on the source
Speechmatics MCP by usefulapi
Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
v1.40.0As shown on registry.modelcontextprotocol.io when we last read it