# Fix list: Speechify API Voice Cloning From Anchor Terminal's listing at https://www.anchorterminal.com/tools/speechify-voice-cloning, the October 2026 research run, assessed 1 October 2026. Grade BB, 74.5 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 Speechify API Voice Cloning: 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-unit overage prices are public, $10, $8 and $6 per million characters by plan (20). The Free plan can't clone and has no voice design (0). Signup is a human browser flow (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. Security & auth, 73 out of 100, up to 4.7 more on the total Why it scored 73: Graded for voice cloning, with consent and misuse controls in place of the read-only line and training and retention of voice data in place of the prompt-injection line, since the API returns audio and IDs rather than third-party text. Service-account keys with scopes (`voices:read`, `voices:write`, `audio:all`), rotation with a grace window, and minted child keys capped at 24 hours (30). Every clone needs a single-use consent challenge, the speaker reads the phrase, and the create call is refused unless the words and speaker match, plus output watermarking with a detection endpoint (20). Customer data isn't used for training per last week's check of the terms, consent recordings are kept as evidence, and no retention period is published (10 of 15). Usage and spend roll up per service account, no per-call log found (8 of 15). security.txt valid per last week's check, no bug bounty, SOC 2 or trust centre found (5 of 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. ## 3. Agent ergonomics, 82 out of 100, up to 2.9 more on the total Why it scored 82: Creating a voice returns a compact voice object (20 of 25, we didn't confirm a filter for listing only personal voices). The SDK paginates lists, filters not confirmed (10 of 20). Machine-readable error codes with a `fields` map for validation failures (20). `Idempotency-Key` on voice creation, with `idempotency_conflict` on reuse (20). Cloning needs two calls and five fields because of the consent step, with official Python and TypeScript SDKs (12 of 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. ## 4. Transparency & trust, 69 out of 100, up to 2.7 more on the total Made of editorial 45, provenance 92. Why it scored 69: Closed service with clear API terms, SDKs under MIT (15 of 30). Terms say customer data isn't used for training and consent recordings are kept, but no retention period, DPA or subprocessor list was found (10 of 30). The September consent change was announced on 13 August, 41 days ahead, and legacy headers have a stated end date in mid-2027 (20). No subprocessors or data locations found (0 of 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): - Domain age: speechify.ai, registered 2023-01-24 (3 years) (7 of 15) ## 5. Maintenance & community, 75 out of 100, up to 2.2 more on the total Why it scored 75: Consent change shipped on 2026-09-23 with API version 2026-09-13 (30). Changelog entries on 13 August, 28 August, 13 September and 23 September (20). Public changelog, no answering support channel confirmed (5 of 15). Official Python and TypeScript SDKs, Python 4.0.0 on 2026-08-18 (15). SDK released within 90 days, Python 3.10 to 3.15 (5 of 10). 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. Reliability, 90 out of 100, up to 2 more on the total Why it scored 90: Status page at status.speechify.ai (Better Stack) with an API component (20). The API shows 100 per cent uptime over 90 days and no incidents (30). Rate and concurrency limits published per plan, 1 to 150 sustained requests a second and 3 to 100 concurrent (15). 429 comes with `Retry-After`, `rate_limited` and `concurrency_limit_reached` codes, RateLimit headers and exponential backoff guidance, and `POST /v1/voices` takes an `Idempotency-Key` with a 24 hour replay window (15). No SLA found (0). Cloning is generally available (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. ## 7. Schema & documentation, 94 out of 100, up to 1 more on the total Why it scored 94: OpenAPI at docs.speechify.ai/build/openapi.json, listed in llms.txt (25). llms.txt per section, Markdown pages and a docs-search MCP server (10). The consent guide and quickstart explain the flow and when a request will be refused (16 of 20). Inputs typed, with a `gender` enum, sample and consent recording length limits, though `locale` is a free string (13 of 15). Each endpoint lists its error codes and statuses, with examples (15). Dated `Speechify-Version` header and a changelog with entries several times a month (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. ## 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. - Whether Python SDK 4.0.0 (2026-08-18) supports the consent challenge fields required since API version 2026-09-13 - security.txt and the no-training statement come from last week's check, we couldn't re-fetch them today - The listing's OpenAPI URL is docs.speechify.ai/openapi.json, while llms.txt gives docs.speechify.ai/build/openapi.json, we didn't confirm which is current - No SLA, SOC 2 report or bug bounty found ## Weaknesses - No cloning on the Free plan - Self-serve clones cover English and five other languages only - API terms forbid end-user uploads, which the consent guide presents as a supported flow - No retention period, DPA or subprocessor list found - The September consent change broke workspaces pinned to older API versions, with 41 days' notice ## 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. - Create the consent challenge only when the speaker is ready. It's single use and short-lived - Show the phrase as returned. Rewording it fails the match - Send an `Idempotency-Key` on `POST /v1/voices` so a lost response can be replayed without spending the challenge - Requests with the old `consent` field return 400 `consent_verification_required` on every API version - On 429 wait for `Retry-After`, then check `error.code` to tell a rate limit from a concurrency cap ## What the review panel asked for - A key-management API - state which SDK version supports consent challenges - state Starter's clone limit - one canonical OpenAPI URL - SDK consent-field support - align the terms and the guide - Publish an uptime SLA - Confirm SDK consent support - Key-management API - a published retention period ## 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.