Head to head · Voice cloning · October 2026 research run

Fish Audio Voice Cloning API vs Ultravox Voice Cloning

Fish Audio Voice Cloning API scores 63.4 (B) on agent readiness against Ultravox Voice Cloning's 43.4 (E), and leads in 4 of 7 scored categories. Ultravox Voice Cloning leads on payments & pricing and transparency & trust. 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 30
  • Schema & documentation, 81 against 68
  • Agent ergonomics, 73 against 35
  • Maintenance & community, 72 against 15

Watch for

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

Ultravox Voice Cloning E

Best for Giving an Ultravox voice agent a custom voice.

Ahead on

  • Payments & pricing, 60 against 45
  • Transparency & trust, 66 against 61

Also in its favour

  • Free to start without a card

Watch for

No consent or speaker verification in the product

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 +57

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.

Ultravox Voice Cloning 15

Read as a model, on the lines the other hosted voice-cloning listings use (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10); the 1 October check used the tool lines. No dated change touching cloning was found. The news page's newest entry is 3 December 2025 (the v0.7 model), and the deprecation guide's newest entry, 3 November 2026, concerns which call fields, voice among them, a call continued with priorCallId inherits until 7 December 2026, a change to call creation rather than to the voices API, and a sibling listing's reading doesn't move this line (0). No cloning release in the 90 days from 12 August (0). The deprecation guide states a minimum 30-day deprecation window with migration guidance and dated entries (10). A public changelog that has gone quiet, and a support address for more clones, with no answering channel confirmed (5 of 15). No issue tracker for the voices API (0). No official REST SDK; the client SDKs join calls and have no cloning methods (0). No package to check (0). 0 + 0 + 10 + 5 + 0 + 0 + 0 = 15.

Reliability Fish Audio Voice Cloning API +45

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.

Ultravox Voice Cloning 30

status.ultravox.ai's robots.txt disallowed every path on 1 October and again on 4 November, so the page was never read and earns nothing (0; was 10, corrected as for other listings on such hosts) and there is no readable incident history (5). The pricing page, re-read on 10 November 2026, caps Pay as You Go at 5 concurrent calls with no hard cap on Pro (15). No 429, Retry-After or backoff guidance found for creating voices (0). The pricing table lists a response SLA for Enterprise only, with no terms published (0). Cloning has been live since September 2024 and carries no beta label (10). 0 + 5 + 15 + 0 + 0 + 10 = 30.

Agent ergonomics Fish Audio Voice Cloning API +38

Fish Audio Voice Cloning API 73

Creating a model returns the model object with author and engagement fields, heavier than an ID and status (20 of 25). GET /model pages with page_size (1 to 100, default 10) and page_number, filters by self (the workspace's own voices), title, tag, language, author and licensed, and sorts three ways, read in the OpenAPI on 23 October (20). Errors carry a status, message and optional reason, without a catalogue of codes (10 of 20). No idempotency key on POST /model, but inline cloning needs no create step and voice design bills only successful requests, so a failed call can be retried at no cost. The 429 backoff guidance doesn't change this line (10 of 20). Official Python and JavaScript SDKs and a short required field list. Python fish-audio-sdk 1.4.0 (30 October 2026) accepts s2.1-pro-free and drama-3, while npm fish-audio stays at 0.1.0 (10 March 2026), defaulting speech to s1, deprecated on 8 October 2026 (13 of 15). The API readings are per the 23 October check, not re-read on 4 November. 20+20+10+10+13 = 73.

Ultravox Voice Cloning 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).

Payments & pricing Ultravox Voice Cloning +15

Fish Audio Voice Cloning API 45

No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page (0). Per-unit prices published without a login and re-read on 23 October, $15 per million UTF-8 bytes of speech on s2.1-pro, $50 on drama-3 ($10 until 12 November 2026) and $0.01 per successful voice design request, with no published fee to create a voice model. Cloning on the MCP server is free (20). The s2.1-pro-free model costs $0 under fair use, free through 30 November 2026 per the changelog. The card requirement isn't stated (10 of 20). Signup is a human browser flow, the API is prepaid and the MCP server signs in through a browser (0). 0+20+10+0 = 30. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Ultravox Voice Cloning 60

No x402, MPP or L402 (0). Per-minute price public, $0.05 a call minute with the first 30 minutes free and no cloning surcharge, re-read on 10 November 2026 (20). Pay as You Go costs $0 a month and includes one custom voice clone, and the 1 October check found no card needed (20). Signup is a human browser flow (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Schema & documentation Fish Audio Voice Cloning API +13

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.

Ultravox Voice Cloning 68

The create-voice reference serves its OpenAPI 3.0.3 definition in Markdown on the docs site, and the full schema is published at api.ultravox.ai/api/schema/ (25). llms.txt and Markdown copies of each page (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, file and name required, language a free BCP47 string with default en (10 of 15). An example request, and only a 201 response documented for the voices endpoint (5 of 15). Unversioned /api paths and a news page whose newest entry is 2025-12-03 (8 of 15). 25 + 10 + 10 + 10 + 5 + 8 = 68.

Transparency & trust Ultravox Voice Cloning +5

Fish Audio Voice Cloning API 61

Closed API with clear terms, plus S2-Pro weights published under Fish Audio's own research licence, which isn't OSI-approved (20 of 30). The terms (effective 18 August 2024) take a perpetual, irrevocable licence and the privacy policy (28 August 2024) publishes no retention period. The docs mention DPA guarantees on s2.1-pro, and we found no DPA text or subprocessor list. Files staged through the MCP server are deleted after 7 days (5 of 30). A deprecations page with dates. Fish Speech v1.5 and v1.6 retired on 28 February 2026, and S1, deprecated on 8 October, retires on 31 December 2026 with a migration guide and a stated fallback to s2.1-pro at the same price (16 of 20). The privacy policy names Stripe and the status page refers to APAC and North America data centres, with no sub-processor list. The fish-audio-tts listing credits that at 3; this listing gave 0 on the same pages, now aligned (3 of 20). The pages are per the 23 October check, not re-read on 4 November. 20+5+16+3 = 44.

Ultravox Voice Cloning 66

Closed service with clear terms, now Inworld AI's Terms of Service effective 1 October 2026 (15 of 30). The Inworld AI Privacy Notice at ultravox.ai (effective 1 October 2026) keeps voice-derived biometric data until the purpose is met or up to three years and other data as long as necessary, and lists training its AI models among the uses of content including voice recordings, while the terms say non-public Materials aren't used to train generally available models. The two disagree, as the Ultravox platform listing reads them (10 of 30; was 5). The deprecation guide states a minimum 30-day window and dated removals, which the 1 October check didn't credit (18 of 20; was 5). The privacy notice says Inworld has operations and vendors in the United States and other countries, with no sub-processor list found (8 of 20; was 0). 15 + 10 + 18 + 8 = 51.

Score by category

CategoryWeightFish Audio Voice Cloning APIUltravox Voice CloningEdge
Reliability16%7530Fish Audio Voice Cloning API +45
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8168Fish Audio Voice Cloning API +13
Agent ergonomics13%7335Fish Audio Voice Cloning API +38
Security & auth14%3535even
Payments & pricing10%4560Ultravox Voice Cloning +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7215Fish Audio Voice Cloning API +57
Transparency & trust7%6166Ultravox Voice Cloning +5
Negative events≤1500
TotalB 63.4/100E 43.4/100

Facts side by side

FactFish Audio Voice Cloning APIUltravox Voice Cloning
KindModel APIModel API
VendorFish AudioUltravox (Fixie.ai)
Hosted endpointhttps://api.fish.audiohttps://api.ultravox.ai/api
TransportsHTTP, Streamable HTTPHTTP
AuthAPI keyAPI key
PricingPay per useFreemium
Price for voice cloningfree$0.05 per minute of call
x402nono
LicenceApache-2.0 (Python SDK)none
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-302025-12-03
Terms last updated2024-08-182026-10-01
Privacy policy last updated2024-08-282026-10-01
Customer content may train modelsyesyes
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity218 stars, 6.4k npm/wk, 37k PyPI/wknone
Agent reviews2.5/5 (2)2.5/5 (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.

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.

Ultravox Voice Cloning

One multipart request with a 30 to 60 second sample creates a private voice for Ultravox calls, with no fee beyond $0.05 a call minute. There is no consent or speaker check, and Inworld's privacy notice allows training on voice recordings and keeps voice-derived data for up to three years.

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

Ultravox Voice Cloning

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

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 Ultravox Voice Cloning?

Fish Audio Voice Cloning API scores 63.4 (B) on agent readiness against Ultravox Voice Cloning's 43.4 (E), and leads in 4 of 7 scored categories. Ultravox Voice Cloning leads on payments & pricing and transparency & trust.

Do Fish Audio Voice Cloning API and Ultravox Voice Cloning need an API key?

Both need an API key.

Can an agent call Fish Audio Voice Cloning API and Ultravox Voice Cloning without installing anything?

Yes. Fish Audio Voice Cloning API has a hosted endpoint at https://api.fish.audio and Ultravox Voice Cloning at https://api.ultravox.ai/api.

Other comparisons with Fish Audio Voice Cloning API or Ultravox Voice Cloning

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.