Soniox Speech-to-Text by Soniox

# Fix list: Soniox Speech-to-Text

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/soniox-stt, the October 2026 research run, assessed 1 October 2026. Grade C, 58.3 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 Soniox 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). Token prices published without a login, with Soniox's own per-hour estimates (20). No free credits for new sign-ups since 2025-10-27 (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. Reliability, 65 out of 100, up to 7 more on the total

Why it scored 65: Instatus page at status.soniox.com with per-region components and a paged history (20). Minor incidents only in the last 90 days. A 9-minute failure to open new EU real-time sessions on 25 August 2026, 45 minutes of Japan real-time overload on 8 September, 70 minutes of failed API key creation on 24 August and a 52-minute console login fault on 17 July (20). Limits published with numbers, 100 requests a minute, 10 concurrent streams and a fixed 300-minute stream cap (15). The limits page says going over may be rate limited but names no status code, Retry-After or backoff (0). No SLA found (0). `stt-rt-v5` and `stt-async-v5` 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.

## 3. Schema & documentation, 60 out of 100, up to 6.5 more on the total

Why it scored 60: No OpenAPI or AsyncAPI file found (0). llms.txt with Markdown pages (10). Guides state purpose and say when to use the real-time or async API (15). Parameters are typed in the docs, but without a machine-readable schema we can't check constraints (10). Examples per guide and an error reference page (15). Versioned `/v1` paths and dated model releases on the models page, but no general changelog (10).

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. Maintenance & community, 30 out of 100, up to 6.1 more on the total

Why it scored 30: The newest dated STT change is `stt-rt-v5` on 2026-06-16, with v4 names routed to v5 from 2026-06-30, more than 90 days ago (10). No dated STT entries in the last 90 days (0). No separate changelog, a community and support page (5). Python and Node 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.

## 5. 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. Project API keys, plus temporary keys that can be restricted and expire, sent in the WebSocket config message rather than the URL (20). Customer audio and transcripts are never used for training (20). Audio and transcripts aren't retained by default, and async files and transcripts auto-delete after 30 days or on a delete call (15). Per-request usage logs with request IDs, duration, tokens and cost (10). SOC 2 Type 2 and ISO/IEC 27001:2022, with documents in the console. 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.

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

Why it scored 70: API reading of the checklist. Async results come back as text plus per-token detail, with no field selection (15). Files and transcriptions are listed through the API, though we didn't confirm the paging parameters (15). An error reference page documents codes (15). No idempotency key. `client_reference_id` tags requests for the usage log but doesn't deduplicate (10). A request needs a model and audio. Official SDKs in Python and Node (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.

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

Made of editorial 70, provenance 86.

Why it scored 78: Closed service with clear terms, last updated 2026-06-29, and an Apache-2.0 Python SDK (15). The security page, limits page and pricing page agree on no training, no default retention and 30-day async deletion (25). Model retirements are dated and old names alias to the new model, though the October 2025 retirement of the preview models was described as accelerated (15). A data residency page names region-specific domains for the US, EU, Japan and India, and 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):

- Domain age: soniox.com, registered 2020-03-23 (6 years) (11 of 15)
- 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.

- What status code or WebSocket error a rate-limited request gets
- Whether the list endpoints paginate with a cursor
- Whether Soniox publishes an SLA or a sub-processor list

## Weaknesses

- No free credits for new accounts since October 2025
- No OpenAPI or AsyncAPI file
- No documented status code, Retry-After or backoff for rate limits
- 10 concurrent streams and a fixed 300-minute cap per stream or file
- No STT changelog entry since June 2026

## 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.

- Pass `audio_url` for public files and skip the upload step. Delete uploaded files or they count against the 10 GB quota for 30 days
- Use the `context` field for names and domain terms
- Buffer audio while the WebSocket connects, then flush it after the config message
- Split anything over 300 minutes. The cap is fixed
- Set `client_reference_id` so failed or duplicate requests can be traced in the usage log

## What the review panel asked for

- Restore a small free trial
- Document the rate-limit status code
- 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.