Gladia Speech-to-Text API + MCP by Gladia

# Fix list: Gladia Speech-to-Text API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/gladia-stt, the October 2026 research run, assessed 1 October 2026. Grade B, 69.7 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 Gladia Speech-to-Text API + MCP: 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. Reliability, 60 out of 100, up to 8 more on the total

Why it scored 60: incident.io status page with per-component uptime bars, 99.90 per cent for Pre-Recorded and 99.95 per cent for Real-Time over the window shown, and incident pages, though no history index we could open (20). One major incident in the last 90 days, a global Pre-Recorded and Real-Time incident on 23 September 2026 from 07:05 to 08:10 caused by a provider network fault. A 20-minute full outage on 22 September, 94 minutes of slow pre-recorded jobs on 7 July and short EU degradations make up the rest (10). Concurrency limits published with numbers, 25 parallel async jobs plus 300 queued and 30 live sessions on paid plans, 3 and 1 on free (15). The docs say a 429 means the concurrency limit, but we found no backoff guidance or Retry-After (5). No SLA found in the security page or docs (0). `solaria-1` and `solaria-3` 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.

## 2. 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 published without a login (20). A one-time €50 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.

## 3. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Plain revocable API keys in the `x-gladia-key` header. Live sessions connect to a WebSocket URL minted per session by `POST /v2/live`, which we don't deduct for (20). Free plan audio may be used for training, paid and Enterprise audio isn't (15). Retention is documented and jobs can be deleted, but zero retention needs Enterprise per the retention page (10). Job history through the list endpoint and dashboard, no audit log of key actions found (10). SOC 2 Type 1 and Type 2, a bug bounty programme that doubles as the disclosure route, no security.txt and no public advisories found. ISO 27001 is in progress, not held (15).

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.

## 4. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: API reading of the checklist. Add-ons such as summaries, NER and translation are opt-in, so a plain request stays small, but there's no field selection (15). Pre-recorded jobs list with offset, limit and filters (20). Documented error codes, with a 429 for concurrency (15). No idempotency key. The docs warn that a job is already queued once the 200 or `transcription.created` webhook arrives, which is safe-retry guidance of a sort (10). One required parameter and official SDKs in JavaScript and Python (15). The official MCP server adds 8 tools for async jobs, which this API reading doesn't score.

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.

## 5. Transparency & trust, 66 out of 100, up to 3 more on the total

Made of editorial 50, provenance 82.

Why it scored 66: Closed service with an MIT SDK and MCP server and separate terms for Gladia SAS and Gladia Inc. (15). The statements disagree. The security page gives a 12-month default retention with 1-day to zero-retention options for customers, while the retention page gives 1 year on free, 3 weeks on paid and zero retention only on Enterprise. ISO 27001 is described as in progress (15). Breaking changes are flagged with dates in the changelog, such as SDK 2.0.0 and the move to credit billing on 3 July 2026 with a 6 to 20 July rollout, but no deprecation policy was found (10). Hosting with a French provider is stated, and no sub-processor list was found (10).

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):

- Domain age: gladia.io, registered 2022-01-11 (4 years) (7 of 15)
- security.txt: not found (0 of 10)

## 6. Maintenance & community, 80 out of 100, up to 1.8 more on the total

Why it scored 80: SDK 2.0.0 for JavaScript and Python on 9 September 2026 and the MCP server on 24 September (30). Six dated changelog entries in the last 90 days (20). Public changelog and support channels. SDK and MCP repository issues not checked in this run (10). SDKs current at 2.0.0, with the breaking change flagged in the changelog (15). 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. Schema & documentation, 95 out of 100, up to 0.8 more on the total

Why it scored 95: OpenAPI file at api.gladia.io/openapi.json (25). llms.txt (10). Reference pages state purpose per endpoint and the model page says to use `solaria-3` only for async English, French, German, Spanish or Italian (15). Typed bodies with enums and required fields, `audio_url` the only required input for pre-recorded (15). Examples per endpoint and documented error codes (15). Versioned `/v2` paths and a dated 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.

## 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.

- Which retention default is current, the security page's 12 months or the docs' 1 year free and 3 weeks paid
- Whether Gladia has an SLA outside Enterprise contracts
- Whether a sub-processor list is published

## Weaknesses

- Starter costs $0.61 an hour async and $0.75 real time, several times the cheapest rivals
- Free-plan audio may be used for training
- The security page and the retention page give different retention defaults
- ISO 27001 is still in progress
- No published SLA and no Retry-After on 429s

## 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.

- Don't resubmit a pre-recorded job after a 200 or a `transcription.created` webhook. It's already queued
- Pick `solaria-3` only for async EN, FR, DE, ES or IT audio. Anything live or multilingual needs `solaria-1`
- A 429 means the concurrency limit, 3 async and 1 live on the free plan. Wait for a running job to finish
- Upgrade off the free plan before sending sensitive audio
- Split files over 135 minutes or 1,000 MB

## What the review panel asked for

- Publish Growth commitment sizes
- Add Retry-After to 429
- Publish an SLA

## 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.