Azure AI Speech speech-to-text by Microsoft Azure

# Fix list: Azure AI Speech speech-to-text

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/azure-speech-to-text, the October 2026 research run, assessed 1 October 2026. Grade BB, 77 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 Azure AI Speech 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-hour prices published without a login, though the page needs JavaScript and the Retail Prices API is the readable source (20). The F0 tier gives 5 real-time hours a month but an Azure subscription needs 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. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: API reading of the checklist. Fast transcription returns combined text plus per-phrase detail, with word timestamps opt-in, but no field selection (15). Batch transcriptions and files list with `top`, `skip` and a next link (20). Error responses carry codes and messages, documented in the REST reference (15). No idempotency key on batch creation (10). Fast transcription needs a key, a file and a locale. Speech SDKs in C#, C++, Java, JavaScript, Python, Go, Objective-C and Swift (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.

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

Why it scored 80: OpenAPI definitions for the speech-to-text REST API are published in Microsoft's public REST API specs (25). No llms.txt found (0). Operation descriptions state purpose, and the speech-to-text overview says when to use real time, fast or batch (15). Batch request bodies are typed with enums and required fields, but fast transcription takes its options as a JSON string in the multipart `definition` field, documented but untyped on the wire (10). The REST reference carries examples and error responses per operation (15). Dated `api-version` values (current GA 2025-10-15) and monthly 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.

## 4. Reliability, 90 out of 100, up to 2 more on the total

Why it scored 90: Azure status page with post-incident reviews (20). No review in the last 90 days names Speech. One on 29 September 2026 covers intermittent 5xx errors for Cognitive Services in Sweden Central from 10:03 to 15:58 UTC, which may touch Speech resources there, so we count it as minor. The public page only lists broad incidents (20). Limits published with numbers, 100 concurrent real-time requests and 600 fast or batch requests a minute by default (15). 429 documented as usually meaning autoscaling in progress, with a 1, 2, 4, 4 minute backoff pattern and advice to ramp load gradually. Fast transcription is synchronous, so a retry doesn't duplicate a job (15). Covered by Microsoft's online services SLA (10). Fast transcription, batch and real time are GA. MAI-Transcribe-2 is preview with no SLA (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.

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

Why it scored 80: Speech SDK 1.52 shipped in September 2026 and MAI-Transcribe-1 was deprecated on 2026-08-20 (30). Release notes for July, August and September 2026 (20). Public release notes, a GitHub samples repository and Microsoft Q&A (10). Speech SDK current in eight languages (15). The SDK itself is a closed binary, so we can't see its CI (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.

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

Made of editorial 80, provenance 95.

Why it scored 88: Closed service under Microsoft's product terms, with an MIT samples repository (15). The data privacy page, the privacy statement and the product terms agree on no storage for real time, retention until deletion for batch and no training (25). Dated retirements, REST API v3.0 and the v3.2 previews on 2026-03-31 and MAI-Transcribe-1 deprecated on 2026-08-20, under Microsoft's published lifecycle policy (20). Regions chosen per resource 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.

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. 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. Two regenerable resource keys for rotation, or Microsoft Entra ID tokens with Azure role-based access, which Microsoft recommends (30). Microsoft doesn't use customer audio to train its models (20). Real-time and fast transcription audio isn't stored, and batch output stays until deleted or `timeToLive` expires (15). Azure Monitor and the activity log record resource actions, though we didn't confirm per-request Speech logging (10). The MSRC disclosure policy, Microsoft's Azure bounty programme, SOC 2 and ISO 27001 reports, and public advisories. The microsoft.com security.txt passed its Expires date on 2026-09-23 (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.

- What MAI-Transcribe-2 will cost after 2026-12-31
- Whether per-request Speech calls appear in Azure Monitor diagnostic logs by default

## Weaknesses

- MAI-Transcribe-2 is preview with no SLA, and its $0.10 promotional price ends on 2026-12-31
- Real-time diarisation and language ID add $0.30 an hour each
- REST API v3.0 and the v3.2 previews were retired on 2026-03-31, and older samples still target them
- No llms.txt, and the pricing page needs JavaScript
- An Azure subscription needs a card, even for the F0 tier

## 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.

- Use fast transcription (`transcriptions:transcribe`) for files under 5 hours and 500 MB, and batch for bulk jobs
- Pin `api-version=2025-10-15`. v3.0 and the v3.2 previews are retired
- On a 429, back off 1, 2, 4 then 4 minutes. It usually means autoscaling, not a quota
- Set `timeToLive` on batch jobs or delete results, otherwise transcripts stay in Microsoft storage
- Don't budget on MAI-Transcribe-2 at $0.10 an hour after 2026-12-31

## What the review panel asked for

- llms.txt (2 reviews)
- card-free trial route
- Idempotency on batch jobs
- a stated MAI-Transcribe-2 price for 2027
- retirement warnings on old samples
- Type the definition field
- Update samples to the current version
- MAI-Transcribe-2 price after 2026
- default batch TTL
- per-request audit logging
- Publish the post-promotion price
- Add an idempotency key to batch creation
- 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.