Google Cloud Speech-to-Text by Google Cloud

# Fix list: Google Cloud Speech-to-Text

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/google-speech-to-text, the October 2026 research run, assessed 1 October 2026. Grade BB, 70.4 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 Google Cloud 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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Per-minute prices with volume tiers published without a login (20). The 60 free V1 minutes and the $300 new-account credit both need a billing account with a card (0). 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. Maintenance & community, 25 out of 100, up to 6.6 more on the total

Why it scored 25: The newest release note is 2025-11-13, Chirp 3 preview in four more regions, 322 days ago (0). No release notes in the last 90 days (0). Release notes, a public issue tracker and paid support (10). Official client libraries in seven or more languages, release dates not checked in this run (10). Package 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.

## 3. Agent ergonomics, 70 out of 100, up to 4.9 more on the total

Why it scored 70: API reading of the checklist. Word timestamps and alternatives are opt-in, and batch output can go inline or to Cloud Storage, but there's no field selection or text-only mode (15). `recognizers` and operations list with `page_size` and `page_token` (20). Standard gRPC status codes with messages, generic rather than Speech-specific (15). Batch runs as a long-running operation with no idempotency key (10). A first call needs a project, OAuth credentials, a `recognizers` path and Cloud Storage for audio over 1 minute. Official SDKs in seven or more languages (10).

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.

## 4. Schema & documentation, 80 out of 100, up to 3.3 more on the total

Why it scored 80: The API surface is public as protocol buffers and a discovery document, a machine-readable contract (25). No llms.txt found (0). Method descriptions state purpose, and the model pages say which model suits which audio, but not when to avoid sync or streaming (15). Typed proto messages with enums and required fields, no free-form blobs (15). Errors follow Google's standard status codes, with samples in the docs but little per-method error detail (10). Versioned v1 and v2 with release notes (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. Reliability, 85 out of 100, up to 3 more on the total

Why it scored 85: Google Cloud status page with a per-product history (20). No Speech-to-Text incident listed since 12 June 2025, so none in the last 90 days, though the public page only shows broad incidents (30). Quotas published with numbers, 300 concurrent streams, 300 sync and 150 batch requests a minute per region, streams up to 5 minutes and sync up to 1 minute (15). The Speech quotas page says nothing about the error a quota breach returns or how to back off, and we don't count Google's general API design guide for this API (0). Speech-to-Text SLA of 99.9 per cent monthly uptime with credits of 10 to 50 per cent (10). Chirp 3 GA since 2025-10-13 in `us` and `eu`, though 82 of its 111 locales are preview (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.

## 6. Transparency & trust, 88 out of 100, up to 1.1 more on the total

Made of editorial 75, provenance 100.

Why it scored 88: Closed service under the Google Cloud terms (15). The data logging page, the terms and the privacy notice agree that audio isn't used for training without opt-in, and a data processing addendum and sub-processor list exist (25). Google Cloud's terms carry a notice period before a GA feature is discontinued, but we found no dated Speech-to-Text deprecation notices (15). `us` and `eu` multi-region endpoints and a public sub-processor list (20).

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.

## 7. Security & auth, 95 out of 100, up to 0.9 more on the total

Why it scored 95: Model reading of the checklist, with training and retention in place of least-privilege and injection lines. OAuth 2.0 with service accounts and IAM roles, scoped per project, no API key in the documented V2 flow (30). Audio isn't used for training unless the project opts in to data logging (20). Streaming and sync audio is processed in memory and not stored, and batch results are kept for a short window (15). Cloud Audit Logs cover Google Cloud APIs, though we didn't confirm which Speech methods they record (10). Valid security.txt, Google's vulnerability reward programme, SOC 2 and ISO 27001, and public Cloud security bulletins (20).

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.

## 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.

- The listing's lastRelease of 2026-09-28 doesn't match the release notes, whose newest entry is 2025-11-13. We scored maintenance on the release notes
- Which Speech-to-Text methods Cloud Audit Logs record by default

## Weaknesses

- No release note since 2025-11-13
- 82 of the 111 Chirp 3 locales are preview
- Sync requests stop at 1 minute and streams at 5 minutes, and batch reads only from Cloud Storage
- No API keys in the documented V2 flow, and the free minutes need a billed project
- The quotas page doesn't say what error a breach returns or how to back off

## 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.

- Call Chirp 3 on the `us` or `eu` endpoint. It isn't listed for the `global` location
- Reopen streams before the 5-minute limit, or use `BatchRecognize` for recordings
- Downmix stereo unless you need channel labels, since each channel is billed
- Set dynamic batch on offline jobs to cut the price from $0.016 to $0.003 a minute
- Back off on `RESOURCE_EXHAUSTED`. The Speech docs don't give a retry interval

## What the review panel asked for

- Add V2 free minutes
- Document quota-breach errors and backoff
- Add an idempotency key

## 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.