Amazon Transcribe by Amazon Web Services

# Fix list: Amazon Transcribe

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-transcribe, the October 2026 research run, assessed 1 October 2026. Grade BB, 73.6 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 Amazon Transcribe: 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 by region published without a login (20). A new AWS account needs a card, and the 60 free minutes apply only to accounts opened before 2025-07-15 (0). A person signs up in a browser. IAM can mint keys by API, but only after a human has an account (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, 35 out of 100, up to 5.7 more on the total

Why it scored 35: The Transcribe document history's newest entry is 2026-07-01, PII redaction for more English dialects, 92 days ago (10). No dated entries in the last 90 days (0). Public document history, AWS re:Post and paid support plans (10). Official SDKs in Python, JavaScript, Java, Go and others, release dates not checked in this run (10). The awslabs Python streaming SDK's state wasn't checked either (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. Security & auth, 80 out of 100, up to 3.5 more on the total

Why it scored 80: Model reading of the checklist, with training and retention in place of least-privilege and injection lines. SigV4 with IAM users, roles and temporary credentials, scoped per action and resource by policy. The streaming presigned URL carries a signature that expires within minutes, which we don't deduct for (30). AWS may store and use content to improve the service by default. Any customer can opt out with an AI services opt-out policy on its AWS organisation (10). Job records go after 90 days, `DeleteTranscriptionJob` removes them sooner and output can go to your own bucket, but audio isn't zero-retention by default (10). CloudTrail logs API calls per caller (15). Vulnerability reporting policy, SOC and ISO reports in AWS Artifact, and public security bulletins (15). The security.txt on aws.amazon.com passed its Expires date on 2026-09-24 and we found no paid public bug bounty (0 of the remaining 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.

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

Why it scored 80: API reading of the checklist. The transcript is one JSON file with every item and its timings, with SRT and VTT subtitles as the compact alternative and no field selection (15). `ListTranscriptionJobs` filters by status and name and pages with `MaxResults` and `NextToken` (20). Typed exceptions per action, each with a recovery hint (20). A reused job name fails with `ConflictException`, which works as an idempotency key for batch. Streaming has no resume (15). Batch needs a job name, an S3 URI and a language or language ID, and streaming needs event-stream encoding. SDKs in every major language (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.

## 5. Schema & documentation, 90 out of 100, up to 1.6 more on the total

Why it scored 90: The service model is public in the AWS SDKs (botocore and the JavaScript v3 clients), a machine-readable contract in the role OpenAPI plays (25). llms.txt for the developer guide (10). Action descriptions state purpose and preconditions, such as uploading to S3 first, but not when to pick streaming over batch (15). Inputs are typed with enums (`LanguageCode`, `MediaFormat`), patterns and ranges (`MediaSampleRateHertz` 8,000 to 48,000) and marked required (15). Every action lists its errors with HTTP codes, but the API reference pages have no examples section, so examples live in the developer guide (10). API version 2017-10-26 and a dated document history (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.

## 6. Transparency & trust, 85 out of 100, up to 1.3 more on the total

Made of editorial 75, provenance 95.

Why it scored 85: Closed service under the AWS Service Terms (15). The service terms, privacy notice and job retention agree, and the data processing addendum and a public sub-processor list exist, but the default permission to use content for improvement sits in the service terms rather than the Transcribe guide (25). The AWS Customer Agreement commits to advance notice before material functionality of a GA service is discontinued, but we found no dated Transcribe deprecation notices (15). Sub-processors and regions disclosed, with region choice per request (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.

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

- security.txt: published but past its Expires date (5 of 10)

## 7. Reliability, 95 out of 100, up to 1 more on the total

Why it scored 95: AWS Health Dashboard with per-service, per-region history and RSS feeds (20). The Transcribe feeds for us-east-1, us-west-2 and eu-west-1 carried no events on 1 October 2026 (30). The public dashboard only lists broad events, and account-level ones go to the personal health dashboard, so a clean feed says less than a small vendor's detailed page. Default quotas published with numbers, 25 concurrent streams, 250 concurrent batch jobs and 25 `StartTranscriptionJob` calls a second per region (15). Throttling returns `LimitExceededException` as an HTTP 400 that says to wait before retrying, with no Retry-After, and unique job names make resubmits safe (10). SLA under the Amazon Machine Learning Language agreement, which names Transcribe (10). 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.

## 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 2026-09-29 doesn't match the document history, whose newest entry is 2026-07-01. We scored maintenance on the document history
- Whether the awslabs amazon-transcribe Python streaming SDK is still released and tested

## Weaknesses

- AWS may store and use audio to improve the service unless an organisation-wide AI services opt-out policy is set
- Batch input must sit in S3, and the WebSocket stream needs a presigned SigV4 URL
- No Transcribe document history entry since 2026-07-01
- Throttling returns `LimitExceededException` as a 400 with no Retry-After
- New accounts need a card, and the free minutes only apply to accounts opened before 2025-07-15

## 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.

- Give every job a unique `TranscriptionJobName`. A retry with the same name fails with `ConflictException` rather than starting a second job
- Batch is a job. Poll `GetTranscriptionJob` or listen on EventBridge, then fetch the transcript URI
- Set `OutputBucketName`, because job records are deleted after 90 days
- Back off on `LimitExceededException`. It arrives as a 400, not a 429
- Set the organisation's AI services opt-out policy before sending customer audio

## What the review panel asked for

- Return a Retry-After on throttling
- Publish a streaming latency figure

## 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.