# Speechmatics — how to use (mcp.ai)

Connect your Speechmatics account and use 7 tools for transcription straight from your AI agent. Connect with your own API key. Speechmatics provides asynchronous speech-to-text transcription, job management, transcript retrieval, and usage reporting for audio and video.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_speechmatics?ms=1787295900000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `speechmatics_create_transcription_job`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/speechmatics`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/speechmatics/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/speechmatics/create/transcription/job` — Create an asynchronous Speechmatics transcription job from a publicly fetchable media URL and return its job ID.
  - body: { model?: string, domain?: string, language: string, job_title?: string, media_url: string, output_locale?: string, enable_entities?: boolean }
- `POST https://api.mcp.ai/api/speechmatics/delete/transcription/job` — Delete a transcription job and its associated transcript and resources, optionally forcing termination of a running job.
  - body: { force?: boolean, job_id: string }
- `POST https://api.mcp.ai/api/speechmatics/discover/speech/features` — Return Speechmatics' current Batch languages, locales, domains, translation support, and language-identification capabilities.
- `POST https://api.mcp.ai/api/speechmatics/get/transcript` — Retrieve a transcription job's completed transcript as structured JSON v2, plain text, or SRT text.
  - body: { format?: string, job_id: string, wait_seconds?: integer }
- `POST https://api.mcp.ai/api/speechmatics/get/transcription/job` — Get a transcription job's status, configuration, duration, and processing errors, optionally waiting briefly for a terminal state.
  - body: { job_id: string, wait_seconds?: integer }
- `POST https://api.mcp.ai/api/speechmatics/get/usage` — Get Batch transcription counts and audio duration aggregated over an optional UTC date range.
  - body: { since?: string, until?: string }
- `POST https://api.mcp.ai/api/speechmatics/list/transcription/jobs` — List transcription jobs in the connected US1 project, newest first, with an agent-controlled continuation cursor.
  - body: { limit?: integer, next_cursor?: string, created_before?: string, include_deleted?: boolean }

## Example prompts
- "What can I do in Speechmatics?"
- "Show me a summary of my Speechmatics account"

## More
- Page: https://mcp.ai/speechmatics
- Agent spec (llms.txt): https://mcp.ai/speechmatics/llms.txt
- Postman collection: https://mcp.ai/speechmatics/postman.json