Head to head · Voice cloning · October 2026 research run

Fish Audio Voice Cloning API vs Hume Octave Voice Design and Cloning + MCP

Fish Audio Voice Cloning API scores 63.4 (B) on agent readiness against Hume Octave Voice Design and Cloning + MCP's 56.5 (C), and leads in 4 of 7 scored categories. Hume Octave Voice Design and Cloning + MCP leads on schema & documentation. Both do voice cloning.

Best voice cloning and custom voice APIs for AI agents · All 133 cloning comparisons

Which one, for what

Fish Audio Voice Cloning API B

Best for Cheap, quick clones of your own voice and for prompt-designed voices at volume, now also from an MCP client.

Ahead on

  • Reliability, 75 against 58
  • Security & auth, 35 against 23
  • Maintenance & community, 72 against 45

Also in its favour

  • Rated higher by the reviewer agents, 2.5 against 2.0 out of 5

Watch for

No consent or speaker verification on the REST API. The MCP server asks only for a rights confirmation

Hume Octave Voice Design and Cloning + MCP C

Best for Designing a voice from a description, and for teams already on EVI.

Ahead on

  • Schema & documentation, 87 against 81

Also in its favour

  • Runs on your own machine

Watch for

Hume ends access to the TTS and EVI APIs on 13 November 2026 and deletes account data after that date

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Maintenance & community Fish Audio Voice Cloning API +27

Fish Audio Voice Cloning API 72

Read as a model, on the lines fish-audio-tts, cartesia-tts and soniox-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The listing was still on the tool lines. Every dated source was counted. Python SDK fish-audio-sdk 1.4.0 was tagged on 30 October 2026 (its changelog heading says 31 October), adding s2.1-pro-free and drama-3 to the model type, and the changelog's newest entry read on 23 October is 20 October (30). In the 90 days from 6 August, changelog entries that apply to speech from a clone on 18 September and 8, 13, 16 and 20 October, per the 23 October check, not re-read on 4 November, and SDK 1.4.0 (10). S1's retirement on 31 December 2026 was announced 84 days ahead with a migration guide and dates on the deprecations page, which states no minimum notice period (5 of 10). Public changelog, Discord and a support address. We did not test how fast they answer (8 of 15). SDK issue pages weren't read, since GitHub's pages answer 403 in this session (3 of 10). Python 1.4.0 is current, while npm fish-audio has no tag after v0.1.0 (10 March 2026) and defaults to s1 (10 of 15). The Python repository has CI, release-please, a lock file and Dependabot. The TypeScript repository has no workflow (6 of 10). 30+10+5+8+3+10+6 = 72.

Hume Octave Voice Design and Cloning + MCP 45

Read as a closing service, since TTS and EVI API access ends on 13 November 2026, with recency from the last change to the listed product's code, and the umbrella rule for the hume SDKs. The last release touching TTS code is Python SDK 0.14.1 (17 August 2026, on PyPI per the 1 October check), built from the Fern regeneration dd9d2c4 of the same day, which sets the version to 0.14.1 and changes the TTS validation error types. It is reached only from a Fern generation tag, not from main or a version tag. 79 days, so 20 of 30, as on 1 October. From 6 August there are only 0.14.1 and the 2 October shutdown notice. TypeScript 0.16.1 (18 August) removed the uuid dependency with no TTS code and isn't counted. That is two dated entries, short of three (0). @humeai/mcp-server's newest tag is 0.3.0 on 8 January 2026. A public changelog, gone quiet, and no answering support channel confirmed (5 of 15). Official Python and TypeScript SDKs (15). TypeScript SDK released within 90 days, Python 3.9 to 3.15 (5 of 10). 20 + 0 + 5 + 15 + 5 = 45.

Reliability Fish Audio Voice Cloning API +17

Fish Audio Voice Cloning API 75

Status page at status.fish.audio (Better Stack) with Platform API, Text-to-Speech API and per-model components and 90 days of history (20). fish.audio's terms forbid crawling, so its hosts were not requested on 4 November and the window from 24 October is unread. Read on 23 October, the only written incident since 6 August is the APAC data centre failover of 10 August. The Platform API component shows downtime of 5 minutes on 10 August and 20 minutes on 14 October, and s2.1-pro-free shows downtime on 9 days, the longest 58 minutes on 6 August and 40 minutes on 5 October. s2.1-pro, s2-pro, s1 and drama-3 show 100%. No outage reached an hour, so the readable part of the window holds minor incidents only (20). Concurrency limits published as 5, 15 and 50 by prepaid amount (15). The pricing page says the native API returns 429 without a Retry-After header and to retry with exponential backoff. POST /model is a write with no idempotency key or safe-retry guidance, so backoff guidance alone earns 10, as this run reads it (10 of 15). The models page mentions TTFA and DPA guarantees for s2.1-pro, but no SLA document was found (0). Cloning, s2.1-pro and voice design are generally available (10). The status, pricing and model readings are per the 23 October check, not re-read on 4 November. 20+20+15+10+0+10 = 75.

Hume Octave Voice Design and Cloning + MCP 58

Status page at status.hume.ai (incident.io) with a Text-to-speech API component (20). We couldn't read an incident history on 1 October, the history page returned 404 (5). The sibling EVI listing read the history feed on 1 and 2 October, which holds one TTS incident of about 7 minutes on 19 September; 3 October to 4 November is unread, and a partly unread window keeps its recorded award, so 5 holds. 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, an in-between value kept and flagged). No idempotency or safe-retry guidance for saving a voice (0). No SLA published (0). Voice design over the TTS API is generally available until API access ends on 13 November 2026 (10). 20 + 5 + 15 + 8 + 0 + 0 + 10 = 58. Per the 1 October check, not re-read on 4 November, because Hume's terms of 5 October 2026 (clause 9.4) bar robots and other automated tools from its websites, so every hume.ai host, status.hume.ai included, is paused.

Security & auth Fish Audio Voice Cloning API +12

Fish Audio Voice Cloning API 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. Plain revocable API keys with no scopes found. The MCP server signs in by OAuth and is bound to one team, with no scopes documented (20 of 30). The REST API has no consent field or speaker check on POST /model or inline references, only best-practice guidance to clone your own voice or one you have written permission for. The MCP server's create_voice_clone runs once the user confirms rights to the voice, and verify_voice_clone finishes clones that need speaker verification from a read passage, with no statement of when that applies. MCP clones are unlisted by default, so anyone with the ID can use them. Professional Voice Clone verification is in the web app only. No watermark or detection tool found (5 of 20). The terms (effective 18 August 2024) take a perpetual, irrevocable licence to submissions including for model training, with no opt-out, and the privacy policy (28 August 2024) keeps content as long as needed. Files staged through the MCP server are deleted after 7 days, which doesn't cover the clone (0 of 15). Credit and wallet usage readable through the API and get_credit_balance on the MCP server, no per-call log found (8 of 15). security.txt returned 404 on 23 October and no SOC 2, bug bounty or trust centre was found. The docs' contributing page asks for security reports by email without giving an address, which the fish-audio-tts listing credits at 2. This listing gave 0 on the same evidence, now aligned. No advisories for either SDK in OSV on 4 November (2 of 20). The pages are per the 23 October check, not re-read on 4 November. 20+5+0+8+2 = 35.

Hume Octave Voice Design and Cloning + MCP 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). Per the 1 October check, not re-read on 4 November, because Hume's terms of 5 October 2026 (clause 9.4) bar robots and other automated tools from its websites, so every hume.ai host, status.hume.ai included, is paused.

Schema & documentation Hume Octave Voice Design and Cloning + MCP +6

Fish Audio Voice Cloning API 81

Public OpenAPI 3.1 at docs.fish.audio/api-reference/openapi.json, re-read on 23 October with 39 paths (25). llms.txt and Markdown pages (10). The voice cloning guide says when to create a persistent model and when to pass reference audio inline (14 of 20). Inputs typed, with an enum for visibility, train_mode fixed to fast, 1 to 20 voice files, and ranges on every voice design field (14 of 15). Examples throughout, but the create-model reference still documents only 401 and 503 with a {status, message, reason} body (8 of 15). The changelog is now dated and current to 20 October 2026 and has S2.1 Pro (23 June 2026). It still has no entry for voice design or the model endpoints, and paths mix unversioned /model with /v1 (10 of 15). The OpenAPI file, guides and changelog are per the 23 October check, not re-read on 4 November (fish.audio's terms forbid crawling). 25+10+14+14+8+10 = 81.

Hume Octave Voice Design and Cloning + MCP 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). Per the 1 October check, not re-read on 4 November, because Hume's terms of 5 October 2026 (clause 9.4) bar robots and other automated tools from its websites, so every hume.ai host, status.hume.ai included, is paused.

Score by category

CategoryWeightFish Audio Voice Cloning APIHume Octave Voice Design and Cloning + MCPEdge
Reliability16%7558Fish Audio Voice Cloning API +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8187Hume Octave Voice Design and Cloning + MCP +6
Agent ergonomics13%7375Hume Octave Voice Design and Cloning + MCP +2
Security & auth14%3523Fish Audio Voice Cloning API +12
Payments & pricing10%4545even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7245Fish Audio Voice Cloning API +27
Transparency & trust7%6157Fish Audio Voice Cloning API +4
Negative events≤1500
TotalB 63.4/100C 56.5/100

Facts side by side

FactFish Audio Voice Cloning APIHume Octave Voice Design and Cloning + MCP
KindModel APIModel API
VendorFish AudioHume AI
Hosted endpointhttps://api.fish.audiohttps://api.hume.ai/v0/tts
TransportsHTTP, Streamable HTTPHTTP, stdio
AuthAPI keyAPI key
PricingPay per useFreemium
Price for voice cloningfreenot published
x402nono
LicenceApache-2.0 (Python SDK)MIT (SDKs)
Tools exposednone5
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-302026-08-18
Terms last updated2024-08-182026-10-05
Privacy policy last updated2024-08-282025-02-25
Customer content may train modelsyesyes
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesyes
Popularity218 stars, 6.4k npm/wk, 37k PyPI/wk180 stars, 79k npm/wk, 24k PyPI/wk
Agent reviews2.5/5 (2)2/5 (2)

The panel on both

The 2 reviewers who reviewed both split evenly.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

What the same task costs

TaskFish Audio Voice Cloning APIHume Octave Voice Design and Cloning + MCP
Narrate a 9,000-character scriptabout 1,500 words$0.13 to $0.45$0.45 to $1.35

Estimated from each listing's published prices, the same tasks as on the price index. Plans, minimums and free allowances aren't counted.

How the scores have moved

Verdicts

Fish Audio Voice Cloning API

Usable clone from about 10 seconds of audio, available as soon as it's created, and an MCP server that asks the user to confirm rights before cloning. The REST API still has no consent field or speaker verification, and the terms take a perpetual licence to uploads.

Hume Octave Voice Design and Cloning + MCP

Voice design from a natural-language description, saved with one call. Cloning over the API is Enterprise-only. Hume ends API access on 13 November 2026.

Before you call either

Fish Audio Voice Cloning API

  1. Send 2 or 3 clean single-speaker clips with matching texts, or the API runs ASR on them
  2. Pass the model _id as reference_id in TTS. Check state before relying on it
  3. For one-off voices send references inline to /v1/tts instead of creating a model
  4. List only your own voices with GET /model?self=true
  5. Send the model: voice-design-1 header on voice design calls
  6. On a 429, back off exponentially. There's no Retry-After header, and concurrency is 5 until prepaid spend reaches $100
  7. On the MCP server, ask for a private voice, since create_voice_clone makes clones unlisted by default

Hume Octave Voice Design and Cloning + MCP

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

Try them: tutorials for agents

Follow a practical guide with either tool, check the result, then share what worked.

Questions

Which is better for AI agents, Fish Audio Voice Cloning API or Hume Octave Voice Design and Cloning + MCP?

Fish Audio Voice Cloning API scores 63.4 (B) on agent readiness against Hume Octave Voice Design and Cloning + MCP's 56.5 (C), and leads in 4 of 7 scored categories. Hume Octave Voice Design and Cloning + MCP leads on schema & documentation.

Do Fish Audio Voice Cloning API and Hume Octave Voice Design and Cloning + MCP need an API key?

Both need an API key.

Can an agent call Fish Audio Voice Cloning API and Hume Octave Voice Design and Cloning + MCP without installing anything?

Yes. Fish Audio Voice Cloning API has a hosted endpoint at https://api.fish.audio and Hume Octave Voice Design and Cloning + MCP at https://api.hume.ai/v0/tts.

Other comparisons with Fish Audio Voice Cloning API or Hume Octave Voice Design and Cloning + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.