Stable Audio API by Stability AI

# Fix list: Stable Audio API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/stable-audio, the October 2026 research run, assessed 1 October 2026. Grade D, 50.3 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 Stable Audio API: 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. Security & auth, 30 out of 100, up to 12.3 more on the total

Why it scored 30: Plain bearer API keys from the self-serve platform dashboard, with no scopes, rotation or expiry documented in what we read (20). No least-privilege mode (0). Returns generated audio, no untrusted content (10). No per-call log or audit trail found (0). No security.txt and no disclosure policy, bug bounty or certification found for the API (0). Separately, the privacy policy (effective 31 July 2025) says Stability uses inputs and outputs to train and improve its models unless you opt out, which we weigh under transparency.

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.

## 2. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Credit prices published without a login, $0.01 a credit, 26 credits for a 3.0 generation and 20 for 2.5 (20). We found no free credits for new accounts documented (0). A person signs up and buys credits (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. Maintenance & community, 15 out of 100, up to 7.4 more on the total

Why it scored 15: Stable Audio 3.0 launched on 2026-05-20, 134 days before this check, and we found nothing later (10). We couldn't count release-note entries in the last 90 days (0). Dated release notes exist, support response not checked (5). No official SDK for the v2beta audio routes (0). No package to judge (0).

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.

## 4. Reliability, 65 out of 100, up to 7 more on the total

Why it scored 65: status.stability.ai loaded on 2 October. It runs on incident.io with one component, 'Stability.ai Platform & Services', data since 27 May 2025 and nothing specific to audio, so we give 15 of 20. Its feed holds one incident in the last 90 days, elevated 500s on generation endpoints on 14 September 2026, resolved with no duration published. That could be minor or one major, so we give 15. Rate limit published in the OpenAPI document, 150 requests every 10 seconds (15). A 429 brings a 60-second timeout, which gives an agent a wait time (8), and failed generations aren't charged, which makes retries safe to spend on (7). No SLA (0). Stable Audio 3.0 is a released model but its routes sit under `/v2beta` (5).

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. Agent ergonomics, 60 out of 100, up to 6.5 more on the total

Why it scored 60: `accept: audio/*` returns raw bytes and `application/json` returns base64, so an agent can keep audio out of its context (15), and the caller sets duration and format (10). Stable Audio 3.0 is submit-then-poll with no webhook and no list endpoint (5). Errors are documented per route (15). Failed generations aren't charged, but there's no idempotency key (10). `duration` defaults to 190 seconds, which is long for a sound effect, and every call is multipart (5). No official SDK for the v2beta routes (0).

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.

## 6. Schema & documentation, 79 out of 100, up to 3.4 more on the total

Why it scored 79: Public OpenAPI document with credit costs per route (25). No llms.txt, and the docs site needs JavaScript (0). Route descriptions cover purpose, limits and what may not be uploaded (no copyrighted audio for audio-to-audio or inpaint) (14). Typed inputs with a 1 to 380 second `duration` (default 190), an `output_format` enum and numeric ranges, sent as multipart form data (13). Error responses and the 100 MB request cap are in the spec (12). Versioned routes and dated 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.

## 7. Transparency & trust, 65 out of 100, up to 3.1 more on the total

Made of editorial 43, provenance 86.

Why it scored 65: Output is owned by the user under the Community Licence, with an enterprise licence above $1M annual revenue. Small and Medium 3.0 weights are open under Stability's own licence, not an OSI one, and Large is API-only (15). The privacy policy (effective 31 July 2025) keeps data 'as long as reasonably necessary' with no periods for uploads or outputs, and says inputs and outputs train Stability's models unless you opt out. Consistent, but thin and training-on by default (10). The 2026-05-20 release moved 3.0 to new async routes while 2 and 2.5 stayed on the old ones, with no written deprecation policy (10). The terms name Stability AI Ltd for the UK, EU and Switzerland and Stability AI US Services Corporation elsewhere, and the privacy policy says data is processed in the US under Standard Contractual Clauses. No subprocessor list found (8).

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: stability.ai, registered 2019-11-06 (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.

- unchecked: free credits for new accounts and whether a card is needed. The pricing page renders only with JavaScript and the OpenAPI document doesn't say
- unchecked: release-note entries after 2026-05-20. The release notes render only with JavaScript in both passes
- How long the 14 September 2026 incident of elevated 500s lasted and whether it hit audio routes
- Prices and the 3.0 route list were re-read from the OpenAPI document on 2 October, not from the pricing page

## Weaknesses

- Stable Audio 3.0 is async only, with polling and no webhook, and inpaint stays on 2 and 2.5
- No vocals documented and no stems
- No official SDK for the v2beta routes, no llms.txt, and the docs site and pricing page need JavaScript
- Privacy policy says inputs and outputs train Stability's models unless you opt out
- No security.txt, and the status page has one component for the whole platform, none for audio

## 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.

- On `stable-audio/*` routes, expect HTTP 202 and an `id`, then poll `GET /v2beta/audio/results/{id}` until 200
- Send `accept: audio/*` for raw bytes, not base64 JSON
- Set `duration`. It defaults to 190 seconds on 3.0
- Wait 60 seconds after a 429 before the next call
- Use the `stable-audio-2` routes for inpainting. 3.0 has no inpaint route

## What the review panel asked for

- Webhook for jobs
- Results list endpoint
- Publish enterprise licence pricing

## 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.