Hume Octave Voice Design and Cloning + MCP by Hume AI

# Fix list: Hume Octave Voice Design and Cloning + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/hume-voice-cloning, the October 2026 research run, assessed 1 October 2026. Grade C, 55.2 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 Hume Octave Voice Design and Cloning + MCP: 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, 23 out of 100, up to 13.5 more on the total

Why it scored 23: 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. One account-wide API key and secret pair, regenerated together (10), and 30 minute OAuth client-credential tokens for clients (5), less 10 because the docs show the API key in a WebSocket query string, `?api_key=` (net 5 of 30). Cloning outside Enterprise happens in the Platform behind a legal agreement checkbox, with no verification (5 of 20). API data isn't used for training, but cloning outside Enterprise is a Platform submission, which may be used unless you opt out in settings, and no retention period is published (5 of 15). Usage is tracked in the portal, no per-call log found for TTS (8 of 15). No security.txt, bug bounty, SOC 2 or trust centre found, HIPAA compliance and a DPA on request are claimed (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.

## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Per-unit overage prices are public, $0.15 per 1,000 characters on Creator down to $0.05 on Business (20). A $0 Free plan includes voice design over the API, but cloning over the API is Enterprise-only and the card requirement isn't stated (10 of 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.

## 3. Reliability, 58 out of 100, up to 8.4 more on the total

Why it scored 58: Status page at status.hume.ai (incident.io) with a Text-to-speech API component and uptime bars from 99.59 to 100 per cent over June to September (20). We couldn't read an incident history, the history page returns 404 (5). Requests per minute are published by plan on the pricing page, 15 on Free and Starter up to 225 on Business (15). Rate limiting returns error E0811 with 'try again later', and the official SDKs retry with exponential backoff (8). No idempotency or safe-retry guidance for saving a voice (0). No SLA published (0). Voice design over the TTS API 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.

## 4. Maintenance & community, 45 out of 100, up to 4.8 more on the total

Why it scored 45: Python SDK 0.14.1 on 2026-08-17, 45 days ago, and no changelog entry since 15 May 2026 (20 of 30). Only one SDK release found in the last 90 days (0 of 20). A public changelog, gone quiet, and no answering support channel confirmed (5 of 15). Official Python and TypeScript SDKs (15). SDK released within 90 days, Python 3.9 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.

## 5. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: The official MCP server has 5 tools, but the JSON TTS endpoint returns base64 audio inside the response, which is heavy in a context window (20 of 25). The voice list paginates and filters by `provider`, so `CUSTOM_VOICE` returns only your voices (20). Named error codes (E0601, E0811 and others) say whether to retry (20). No idempotency key and no job to poll, a design call simply runs again (0 of 20). Few required fields, official Python and TypeScript SDKs (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.

## 6. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 40, provenance 86.

Why it scored 63: Closed service with clear terms, SDKs under MIT (15 of 30). The privacy statement says API data isn't used for training and also that anonymised EVI API data is used by default, a DPA is on request only, and no retention period or subprocessor list is published (10 of 30). Dated deprecations in the changelog, EVI 1 and 2 retired on 30 August 2025 after six weeks' notice (15 of 20). No subprocessor list 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: hume.ai, registered 2020-04-06 (6 years) (11 of 15)
- security.txt: not found (0 of 10)

## 7. Schema & documentation, 87 out of 100, up to 2.1 more on the total

Why it scored 87: OpenAPI and AsyncAPI files at dev.hume.ai/openapi.json and asyncapi.json, listed in llms.txt (25). llms.txt and Markdown pages (10). The voice guides explain designing from a description and saving a generation, with less on when not to use it (12 of 20). Inputs typed, utterances take a description and text, saving takes a generation ID and a name (12 of 15). Examples throughout and a page of named error codes with fixes (13 of 15). Versioned `/v0` paths and a public changelog (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.

- We couldn't read Hume's incident history, the history page returns 404
- Whether the Free plan needs a card
- Whether Hume holds a SOC 2 or ISO 27001 certificate, none was found on the pages we read
- The privacy statement contradicts itself on training with EVI API data

## Weaknesses

- Cloning over the API is Enterprise-only
- Consent is a legal checkbox in the Platform, not a check
- One account-wide API key, shown in a WebSocket query string in the docs
- No changelog entry since 15 May 2026
- No security.txt, SOC 2 report or subprocessor list found

## 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.

- Design with `POST /v0/tts` using an utterance `description` plus sample `text`, then save a `generation_id` with `POST /v0/tts/voices`
- Request several generations and pick one. A saved voice can't be tuned afterwards
- List your own voices with `GET /v0/tts/voices?provider=CUSTOM_VOICE`
- Use `/v0/tts/file` or streaming rather than the JSON endpoint to keep base64 audio out of context
- On E0811 back off and retry, the request was rate limited

## What the review panel asked for

- Clone endpoint below Enterprise
- Rename over the API
- scoped API keys
- header-only auth

## 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.