# io.usefulapi/speechmatics (remote · speechmatics.usefulapi.io)

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

- Trust score: 73/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `speechmatics.usefulapi.io`: 73/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-speechmatics/speechmatics.md), [page](https://verifymcp.io/servers/io-usefulapi-speechmatics/speechmatics)

## Channel facts

- Endpoint: `https://speechmatics.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 78/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 823 tokens (~117/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http io-usefulapi-speechmatics https://speechmatics.usefulapi.io/mcp
```

### Codex

```toml
[mcp_servers.io-usefulapi-speechmatics]
url = "https://speechmatics.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-speechmatics": {
      "type": "remote",
      "url": "https://speechmatics.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-speechmatics --url https://speechmatics.usefulapi.io/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-speechmatics:
    url: "https://speechmatics.usefulapi.io/mcp"
```

### Other

```json
{
  "mcpServers": {
    "io-usefulapi-speechmatics": {
      "type": "http",
      "url": "https://speechmatics.usefulapi.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 73, +45)

- [security improvement] Authorization: unverified → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 28, +10)

- [security improvement] Transport: fail → pass

### 2026-08-01 (score 18, −53)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.13 → unverified
- [security regression] Authorization: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: fail → unverified

### 2026-07-31 (score 71, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 69, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 70, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-27 (score 69, +57)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 12)

First indexed and scored.

## MCP tools (7)

### `speechmatics_list_jobs` (~81 tokens)

List jobs

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

Input parameters:

- `created_before` (string): RFC3339 date-time; only return jobs created before this time (for pagination).
- `include_deleted` (boolean): Include deleted jobs in the results.
- `limit` (integer): Max jobs to return.

### `speechmatics_get_job` (~70 tokens)

Get job

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}.

Input parameters:

- `job_id` (string, required): The job id returned by speechmatics_transcribe_url.

### `speechmatics_get_transcript` (~106 tokens)

Get transcript

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.

Input parameters:

- `format` (string): Output format. Default txt for readability; use json-v2 for structured results.
- `job_id` (string, required): The job id.

### `speechmatics_get_job_log` (~50 tokens)

Get job log

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

Input parameters:

- `job_id` (string, required): The job id.

### `speechmatics_get_usage` (~59 tokens)

Get usage

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

Input parameters:

- `since` (string): Start date, YYYY-MM-DD.
- `until` (string): End date, YYYY-MM-DD.

### `speechmatics_transcribe_url` (~385 tokens)

Transcribe audio/video from URL

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.

Input parameters:

- `additional_vocab` (array): Custom vocabulary — strings, or objects like {"content":"gnocchi","sounds_like":["nyohki"]}.
- `diarization` (string): Speaker labeling: speaker (who spoke) | channel (per audio channel) | none.
- `domain` (string): Domain-specific model hint, e.g. finance.
- `enable_entities` (boolean): Emit formatted entities (numbers, dates) in results.
- `fetch_auth_headers` (array): Auth headers to send when fetching a private URL, e.g. ["Authorization: Bearer xyz"].
- `language` (string): Transcription language code, e.g. en, es, de, fr.
- `notification_url` (string): Webhook URL to POST the transcript to when the job completes.
- `operating_point` (string): Accuracy/speed tradeoff. enhanced is more accurate; standard is faster/cheaper.
- `output_locale` (string): Output spelling locale, e.g. en-US, en-GB.
- `summarize` (boolean): If true, also produce a summary of the transcript.
- `summary_content_type` (string): Summary content style (when summarize=true).
- `summary_length` (string): Summary length (when summarize=true).
- `summary_type` (string): Summary layout (when summarize=true).
- `translation_target_languages` (array): Language codes to also translate the transcript into, e.g. ["es","de"].
- `url` (string, required): Publicly reachable audio/video URL for Speechmatics to fetch and transcribe.

### `speechmatics_delete_job` (~72 tokens)

Delete job

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

Input parameters:

- `force` (boolean): Delete even if the job is still running.
- `job_id` (string, required): The job id to delete.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-usefulapi-speechmatics/speechmatics#diagnostics

## Score history

- 2026-08-03: 73
- 2026-08-02: 28
- 2026-08-01: 18
- 2026-07-31: 71
- 2026-07-30: 69
- 2026-07-29: 70
- 2026-07-28: 70
- 2026-07-27: 69
- 2026-07-26: 12

## Links

- Remote endpoint: https://speechmatics.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-speechmatics/speechmatics/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-speechmatics/speechmatics/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-speechmatics/speechmatics