Speechmatics MCP by usefulapi

Server Details

Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Uptime: 82.6% over 54 days
Last Tested: 2026-10-10 13:56
Transport: Streamable HTTP · MCP 2025-06-18
URL
Repository: m190/usefulapi-mcp
GitHub Stars: 0

TDQS

A4.4/5.0

Scored 2026-08-02 07:55 across 7 tools

Disambiguation5/5

Each tool targets a distinct resource and action: job management (get, delete, list), transcript retrieval, usage stats, and submission. No overlapping purposes; the only pair that could seem similar (get_job vs get_transcript) is clearly differentiated by descriptions of status vs content.

Naming Consistency5/5

All tool names follow the exact pattern `speechmatics_<verb>_<object>`, using consistent snake_case. This is highly predictable and makes the API surface easy to navigate.

Tool Count5/5

With 7 tools, the set is well-scoped for a transcription service. Each tool covers a necessary operation without redundancy, and the count feels neither too thin nor overwhelming.

Completeness5/5

The toolset covers the full lifecycle of transcription jobs: create (transcribe_url), read (list_jobs, get_job), retrieve output (get_transcript), delete (delete_job), plus operational needs (get_job_log, get_usage). No significant gaps for the stated purpose.

Available Tools

7 tools

speechmatics_delete_jobDelete job

Destructive

Inspect

⚠️ Permanently deletes a job and its transcript. Set force=true to delete even while it is still running. Batch API: DELETE /jobs/{job_id}.

ParametersJSON Schema

Name	Required	Description	Default
`force`	No	Delete even if the job is still running.
`job_id`	Yes	The job id to delete.

speechmatics_get_jobGet job

Read-only

Inspect

Get a single job's details and status (running | done | rejected | deleted | expired). Poll this until status is "done", then fetch the transcript. Batch API: GET /jobs/{job_id}.

ParametersJSON Schema

Name	Required	Description	Default
`job_id`	Yes	The job id returned by speechmatics_transcribe_url.

speechmatics_get_job_logGet job log

Read-only

Inspect

Get a job's plain-text processing log — useful for debugging a rejected job. Batch API: GET /jobs/{job_id}/log.

ParametersJSON Schema

Name	Required	Description	Default
`job_id`	Yes	The job id.

speechmatics_get_transcriptGet transcript

Read-only

Inspect

Get a completed job's transcript. format=txt (default, human-readable) | srt (subtitles) | json-v2 (structured words, timings, speakers, translations, summary). Only works once the job status is "done". Batch API: GET /jobs/{job_id}/transcript.

ParametersJSON Schema

Name	Required	Description	Default
`format`	No	Output format. Default txt for readability; use json-v2 for structured results.
`job_id`	Yes	The job id.

speechmatics_get_usageGet usage

Read-only

Inspect

Get usage statistics (transcription minutes) for the account over a date range. Batch API: GET /usage.

ParametersJSON Schema

Name	Required	Description	Default
`since`	No	Start date, YYYY-MM-DD.
`until`	No	End date, YYYY-MM-DD.

speechmatics_list_jobsList jobs

Read-only

Inspect

List transcription jobs (most recent first), with status/data_name/duration. Batch API: GET /jobs.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Max jobs to return.
`created_before`	No	RFC3339 date-time; only return jobs created before this time (for pagination).
`include_deleted`	No	Include deleted jobs in the results.

speechmatics_transcribe_urlTranscribe audio/video from URLInspect

Submit a publicly reachable audio/video URL for speech-to-text transcription (optionally with diarization, translation, and summarization). ASYNC: returns a job id immediately — poll speechmatics_get_job until status is "done", then call speechmatics_get_transcript. Batch API: POST /jobs.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes	Publicly reachable audio/video URL for Speechmatics to fetch and transcribe.
`domain`	No	Domain-specific model hint, e.g. finance.
`language`	No	Transcription language code, e.g. en, es, de, fr.	en
`summarize`	No	If true, also produce a summary of the transcript.
`diarization`	No	Speaker labeling: speaker (who spoke) \| channel (per audio channel) \| none.
`summary_type`	No	Summary layout (when summarize=true).
`output_locale`	No	Output spelling locale, e.g. en-US, en-GB.
`summary_length`	No	Summary length (when summarize=true).
`enable_entities`	No	Emit formatted entities (numbers, dates) in results.
`operating_point`	No	Accuracy/speed tradeoff. enhanced is more accurate; standard is faster/cheaper.
`additional_vocab`	No	Custom vocabulary — strings, or objects like {"content":"gnocchi","sounds_like":["nyohki"]}.
`notification_url`	No	Webhook URL to POST the transcript to when the job completes.
`fetch_auth_headers`	No	Auth headers to send when fetching a private URL, e.g. ["Authorization: Bearer xyz"].
`summary_content_type`	No	Summary content style (when summarize=true).
`translation_target_languages`	No	Language codes to also translate the transcript into, e.g. ["es","de"].