Speechmatics Speech-to-Text by Speechmatics

# Fix list: Speechmatics Speech-to-Text

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/speechmatics-stt, the October 2026 research run, assessed 1 October 2026. Grade B, 67.3 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Speechmatics Speech-to-Text: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-hour prices for every model published without a login (20). $100 credit with no card (20). A person signs up in a browser (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Security & auth, 65 out of 100, up to 6.1 more on the total

Why it scored 65: Model reading of the checklist, with training and retention in place of least-privilege and injection lines. API keys as bearer tokens, with a separate management token for key administration (20). Browser and realtime clients pass short-lived JWTs as `?jwt=` on the WebSocket URL with a lifetime the caller sets, so we deduct half (minus 5). Training is opt-in only, and opting in buys a 33 per cent discount (20). Realtime audio isn't stored, batch data is deleted after 7 days or on request (15). A usage reporting service exists, but we found no per-request audit log (10). ISO/IEC 27001:2022 and SOC 2 Type II with a SafeBase trust portal. No security.txt, disclosure policy, bug bounty or public advisories found (5).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 3. Reliability, 70 out of 100, up to 6 more on the total

Why it scored 70: Statuspage at status.speechmatics.com with components per region and history (20). Thirteen entries between 16 July and 10 September 2026, five of them scheduled database maintenance. None was a major outage of a transcription API. The longest were a 2-hour batch slowdown in Australia on 10 August, 64 minutes of TLS errors for a subset of US realtime sessions on 10 September and a 2-hour portal sign-in outage on 16 July (20). Limits published with numbers, 10 new batch jobs and 50 status calls a second, 20,000 concurrent jobs, and 2 or 50 realtime sessions by plan (15). Both limits return 429 with a reason, but the docs only suggest notifications instead of polling and give no backoff or Retry-After (5). No SLA found for self-serve plans (0). Batch, Realtime and Agent STT on `/v2/agent` are GA (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 4. Schema & documentation, 65 out of 100, up to 5.7 more on the total

Why it scored 65: No OpenAPI or AsyncAPI file linked from the docs (0). llms.txt (10). Reference and guide pages state purpose, and the model page says what Melia 1 lacks, such as custom dictionary and translation (15). Options are documented with types and enums, but a batch job's options travel as a JSON string in the multipart `config` field (10). Examples per feature and documented errors, 429 reasons, 404 `expired` after 7 days and `Job rejected` (15). Versioned `/v2` paths and a dated public changelog (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 5. Agent ergonomics, 80 out of 100, up to 3.3 more on the total

Why it scored 80: API reading of the checklist. Transcripts can be fetched as `txt`, `json-v2` or `srt` (20). The jobs list pages by creation date and limit (20). Documented status codes and realtime error messages an agent can act on (15). No idempotency key on job creation (10). A batch job needs a file and a language. Official SDKs in Python and JavaScript, split into batch and realtime packages (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 6. Maintenance & community, 75 out of 100, up to 2.2 more on the total

Why it scored 75: Changelog entries on 28 and 30 September 2026 for Realtime and Batch SaaS (30). Ten dated entries in September 2026 alone (20). Public changelog and support. SDK repository issues not checked in this run (10). Python and JavaScript SDKs published, release dates not checked in this run (10). CI not checked (5).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 78 out of 100, up to 1.9 more on the total

Made of editorial 65, provenance 90.

Why it scored 78: Closed service with clear terms and MIT SDKs (15). The pricing page, limits page and security page agree on opt-in training, 7-day batch retention and no storage for realtime (25). The changelog announces behaviour changes in advance, such as the 23 September 2026 switch to waiting polls, but we found no deprecation policy (10). EU1, US1 and AU1 regions documented per endpoint and the service named as Azure-hosted, but no sub-processor list was found (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- security.txt: not found (0 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Whether Speechmatics publishes an OpenAPI or AsyncAPI file anywhere outside the docs navigation
- The maximum lifetime of a realtime JWT
- Whether a sub-processor list is published

## Weaknesses

- Enhanced costs $0.40 to $0.43 an hour, above most rivals
- No OpenAPI or AsyncAPI file linked from the docs
- 429s carry a reason but no Retry-After or backoff guidance
- Realtime JWTs travel in the WebSocket URL
- Free plan allows 2 realtime sessions

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Set `"model": "enhanced"` explicitly. The default is `standard`
- Use notifications instead of polling. Polling waits 5 seconds by default since the 23 September 2026 change, and `wait=0` turns that off
- Fetch batch transcripts within 7 days. After that the API returns 404 `expired`
- Pass a `fetch_data` URL for files over 1 GB
- Use `/v2/agent` with `linden-1` for live agents instead of the plain realtime path

## What the review panel asked for

- Add Retry-After to 429
- Publish an SLA for self-serve plans

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.