Ultravox Voice Cloning by Ultravox (Fixie.ai)

# Fix list: Ultravox Voice Cloning

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/ultravox-voice-cloning, the October 2026 research run, assessed 1 October 2026. Grade E, 41 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 Ultravox 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. Reliability, 40 out of 100, up to 12 more on the total

Why it scored 40: A status page exists at status.ultravox.ai, but its robots.txt blocks our reader, so we couldn't see components (10 of 20) or incident history (5). The pricing page caps Pay as You Go at 5 concurrent calls (15). No 429, Retry-After or backoff guidance found (0). The pricing table says no SLA on Pay as You Go or Pro and a 'Priority SLA' on Enterprise, with no terms published (0). Cloning has been live since September 2024 (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.

## 2. Security & auth, 35 out of 100, up to 11.4 more on the total

Why it scored 35: 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. `X-API-Key` keys created in the console, no scopes found (20 of 30). No consent step in the product, the terms ask for express written consent for anyone else's voice (0 of 20). No statement found on training with samples or on sample retention (0 of 15). Call History in the dashboard records each call that uses the voice (15). No security.txt, bug bounty, SOC 2 or trust centre found (0 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, 35 out of 100, up to 10.6 more on the total

Why it scored 35: Creating a voice returns a small voice object (20 of 25). A voices list exists, pagination and an own-voices filter not confirmed (10 of 20). No error codes documented for voices (0 of 20). No idempotency key and no job to poll (0 of 20). Few required fields, but no official REST SDK, only client SDKs for joining calls (5 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. Maintenance & community, 5 out of 100, up to 8.3 more on the total

Why it scored 5: Newest changelog entry 2025-12-03, more than 180 days ago (0). No dated entries in the last 90 days (0). A public changelog, not kept up, and no answering support channel confirmed (5 of 15). No official SDK for the REST API (0). No package to check (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.

## 5. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-minute price public, $0.05 a call minute with no cloning surcharge (20). Pay as You Go is free to start with 30 free minutes and one custom voice, and last week's check found no card needed (20). 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.

## 6. Schema & documentation, 68 out of 100, up to 5.2 more on the total

Why it scored 68: OpenAPI schema at api.ultravox.ai/api/schema/ (25). llms.txt (10). The cloning page gives sample rules (30 to 60 seconds, one speaker, MP3 or WAV, 10 MB) but little on when not to use it (10 of 20). Multipart fields typed in the schema, no enum for language confirmed (10 of 15). An example request, no error responses documented for the voices endpoint (5 of 15). Unversioned `/api` paths and a changelog whose newest entry is 2025-12-03 (8 of 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, 54 out of 100, up to 4 more on the total

Made of editorial 25, provenance 82.

Why it scored 54: Closed service with clear terms (15 of 30). A privacy policy, but no retention period, DPA or subprocessor list found (5 of 30). The changelog records model changes with dates but no deprecation notices or policy (5 of 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: ultravox.ai, registered 2023-10-05 (2 years) (7 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.

- The status page is blocked by robots.txt, so reliability rests on pricing and docs alone
- The cloning docs say one voice per account, the pricing page says five on Pro
- Whether the free plan needs a card, taken from last week's check
- Whether samples are used for training or how long they're kept

## Weaknesses

- No consent or speaker verification, only a warranty in the terms
- Clones work only inside Ultravox calls
- No documented errors, retry guidance or REST SDK
- Changelog's newest entry is 2025-12-03
- Docs say one clone per account, the pricing page says five on Pro

## 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.

- Send a single clean, single-speaker MP3 or WAV of 30 to 60 seconds, 10 MB at most
- Expect one clone per account unless support raises it, whatever the plan page says
- Test the voice in the Playground before putting it on a live agent
- Get the speaker's written consent first, the terms require it and Ultravox doesn't check

## What the review panel asked for

- Error docs for voices
- Settle the clone limit
- a separate cloning scope
- a published retention statement

## 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.