Head to head · Voice cloning · October 2026 research run

Cartesia Voice Cloning API + MCP vs ElevenLabs Voice Cloning and Voice Design API

ElevenLabs Voice Cloning and Voice Design API scores 78.7 (A) on agent readiness against Cartesia Voice Cloning API + MCP's 58.9 (C), and leads in 6 of 7 scored categories. Both do voice cloning.

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

Which one, for what

Cartesia Voice Cloning API + MCP C

Best for Teams that want cheap instant clones and fast streaming TTS in the same account, especially voice agents.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No consent or speaker verification in the clone API

ElevenLabs Voice Cloning and Voice Design API A

Best for Teams that need instant clones, professional clones and prompt-designed voices in one account, with consent checks on the professional tier.

Ahead on

  • Schema & documentation, 91 against 85
  • Agent ergonomics, 88 against 65
  • Security & auth, 84 against 42
  • Payments & pricing, 45 against 15
  • Transparency & trust, 83 against 73

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.5 against 2.5 out of 5
  • No incidents deducted, where Cartesia Voice Cloning API + MCP loses 3 points for them

Watch for

Instant clones rely on an attestation, not a check

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.

Security & auth ElevenLabs Voice Cloning and Voice Design API +42

Cartesia Voice Cloning API + MCP 42

Graded on the model lines with the voice-cloning substitutions this run uses (consent and misuse controls in place of the read-only line, training and retention of voice data in place of the prompt-injection line), on the same evidence and values as cartesia-tts and cartesia-ink-stt where it is shared. Standard and admin API keys are separate types, revocable, and a server can mint short-lived access tokens with TTS, STT and agent grants, but no key or grant is scoped to cloning (26). Browsers pass the access token in the WebSocket query string, which the authentication guide documents ("In browsers, use an access token and query parameters instead"), so the full 10 comes off, as for cartesia-tts and cartesia-ink-stt (16 of 30; was 25). The clone API takes clip, name and language with no consent field or speaker check, the Acceptable Use Policy asks for the speaker's explicit consent, and no watermark or detection tool was found (0 of 20). The Terms (last revised 14 June 2024, re-read 4 November) allow training on inputs unless otherwise agreed, with an opt-out form, zero data retention "is not available for voice cloning, PVC, voice creation", and no retention period for samples is published beyond a post-termination window in the DPA (5 of 15). Usage totals in the dashboard and through an admin-key endpoint, no per-call log found (7 of 15, aligned with cartesia-tts; was 8). security.txt at www.cartesia.ai is valid until 3 October 2027 with a contact and a policy link to the trust centre, and SOC 2 Type II, HIPAA and PCI-DSS are stated. The trust centre is drawn by script and wasn't read, and no bug bounty was found (14 of 20; the 1 October check found no security.txt, 10). 16+0+5+7+14 = 42.

ElevenLabs Voice Cloning and Voice Design API 84

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. API keys can be limited to chosen endpoints, given a credit quota, user keys can expire after 15 minutes to 30 days, service-account keys exist and accept an expiry of up to 90 days since 26 October, keys can be limited to IP ranges, and leaked keys are disabled through GitHub secret scanning (30). PVC is own-voice only and needs a spoken verification matched to the samples, IVC relies on an attestation, high-risk and celebrity voices are blocked, and an AI speech classifier and C2PA support are public (14 of 20). Training on content is on by default with a self-serve opt-out, and the privacy policy caps voice data retention at 3 years after the last interaction (10 of 15). The History API lists each generation with voice, model, characters and date (15). security.txt valid to 2027-10-06 (re-read on 1 November, contact elevenlabs.io/security/report) with a disclosure programme, SOC 2 Type II, and a trust centre at compliance.elevenlabs.io, no paid bug bounty found (15 of 20).

Payments & pricing ElevenLabs Voice Cloning and Voice Design API +30

Cartesia Voice Cloning API + MCP 15

No x402, MPP or L402 (0). Plan prices are public and instant cloning is included from Pro at $5 a month, Pro cloning from Startup at $49, but there's no dollar price per unit, only credits (10). The Free plan has no cloning, re-read on 4 November (0). Signup is a human browser flow (0). 0+10+0+0 = 10. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.

ElevenLabs Voice Cloning and Voice Design API 45

No x402, MPP or L402 (0). Per-unit prices for speech from a clone are public, such as $0.08 per 1,000 characters for TTS v4 on the API pricing page (20). The Free plan needs no card, per the 6 October check (the pricing page read on 1 November doesn't say either way), and includes Voice Design, but no cloning (10 of 20). Signup is a human browser flow (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Agent ergonomics ElevenLabs Voice Cloning and Voice Design API +23

Cartesia Voice Cloning API + MCP 65

Responses are compact voice objects, but we found no filter to list only your own voices, and the MCP server loads 19 tools (20 of 25). Voice lists paginate, with auto-paginating SDK iterators, filters not confirmed (10 of 20). Errors are HTTP statuses mapped to SDK exceptions, without cloning-specific codes (10 of 20). No idempotency key. Pro clone fine-tunes expose a status to poll (10 of 20). Three required fields plus the version header, and official Python and TypeScript SDKs (15).

ElevenLabs Voice Cloning and Voice Design API 88

Creating a clone returns only voice_id and requires_verification, and GET /v2/voices can be narrowed to personal or cloned voices (25). Cursor pagination with page_size up to 100 and filters by type, category, fine-tuning state and labels (20). Errors carry a type, a named code and a param for validation failures, with recovery hints on many codes such as voice_not_found, invalid_cursor and concurrent_modification, though the two concurrency codes in different pages disagree (18 of 20, up from 15). No idempotency key, PVC exposes fine_tuning_state to poll (10 of 20). Two required fields for an instant clone, and official Python and TypeScript SDKs among others (15).

Transparency & trust ElevenLabs Voice Cloning and Voice Design API +10

Cartesia Voice Cloning API + MCP 73

Closed service with clear terms (last revised 14 June 2024, re-read 4 November), SDKs under Apache-2.0 (15 of 30). Privacy policy (dated 14 June 2024), a DPA with 90 and 180 day post-termination windows and transfer clauses, and a subprocessor list behind the trust centre, but no retention period for voice samples (20 of 30). Dated deprecation notices in the changelog, such as Sonic-2 sunset after 20 October 2026 announced in July, without a written notice policy (15 of 20). Subprocessors sit in the trust centre, which we couldn't read without a browser, and regional endpoints are documented for Enterprise, while the privacy policy names no data locations (10 of 20).

ElevenLabs Voice Cloning and Voice Design API 83

Closed service with clear terms, SDKs under MIT (15 of 30). Privacy policy updated 9 October 2026 (unchanged on 1 November), still with a 3 year retention cap for voice data and a training opt-out under Data use, a DPA, subprocessors through the compliance portal and a training opt-out that matches the Terms, but the Terms (last updated 9 October 2026, unchanged on 1 November) also take a perpetual, irrevocable licence to User Voice Models while promising deletion on request, which sit uneasily together (25 of 30). Dated deprecations in the changelog, no written notice policy found (15 of 20). Data locations named (United States, the Netherlands, Singapore) and Enterprise residency in the EU, India and Singapore (20).

Schema & documentation ElevenLabs Voice Cloning and Voice Design API +6

Cartesia Voice Cloning API + MCP 85

OpenAPI files for the latest and each dated API version are listed in llms.txt (25). llms.txt and Markdown pages served (10). The cloning guides say when to use an instant clone and when to move to a Pro clone (14 of 20). Clone inputs are typed, with a language enum, an access enum, a 32 character tagline limit and accepted file formats, and clip, name and language required (13 of 15). Examples in curl and both SDKs, but the clone endpoint's OpenAPI lists only a 200 response, with errors on a general API errors page and SDK exception classes (8 of 15). Dated Cartesia-Version header (2026-08-14 the only accepted value on the clone endpoint) and a monthly changelog (15). Re-read on 4 November.

ElevenLabs Voice Cloning and Voice Design API 91

Public OpenAPI at api.elevenlabs.io/openapi.json, 313 paths per the 6 October check, not re-read on 17 October or 1 November because api.elevenlabs.io's robots.txt now disallows every path (25). llms.txt and Markdown docs, with a .md twin of every page (10). The cloning guides say when to use IVC or PVC and warn that more than 3 minutes of IVC audio can make a clone worse (16 of 20). Inputs are typed, but labels is a free-form map (11 of 15). Plenty of examples, and an errors reference in the API docs lists 10 error types with their HTTP statuses and about 70 named codes, though endpoint pages in the OpenAPI still list only 200 and 422 (14 of 15, up from 10, which read the codes as living only in help-centre articles). Versioned paths (/v1, /v2) and a changelog published several times a month, the latest entries dated 12, 19 and 26 October (15).

Score by category

CategoryWeightCartesia Voice Cloning API + MCPElevenLabs Voice Cloning and Voice Design APIEdge
Reliability16%7373even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8591ElevenLabs Voice Cloning and Voice Design API +6
Agent ergonomics13%6588ElevenLabs Voice Cloning and Voice Design API +23
Security & auth14%4284ElevenLabs Voice Cloning and Voice Design API +42
Payments & pricing10%1545ElevenLabs Voice Cloning and Voice Design API +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8485ElevenLabs Voice Cloning and Voice Design API +1
Transparency & trust7%7383ElevenLabs Voice Cloning and Voice Design API +10
Negative events≤15-30
TotalC 58.9/100A 78.7/100

Facts side by side

FactCartesia Voice Cloning API + MCPElevenLabs Voice Cloning and Voice Design API
KindModel APIModel API
VendorCartesiaElevenLabs
Hosted endpointhttps://api.cartesia.aihttps://api.elevenlabs.io/v1
TransportsHTTP, Streamable HTTP, stdioHTTP, stdio
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 (SDKs)MIT (SDKs)
Tools exposed19none
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-302026-10-27
Terms last updated2024-06-142026-03-31
Privacy policy last updated2024-06-142026-05-20
Customer content may train modelsyes, with an opt-outyes, with an opt-out
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 textyes
Arbitration or class-action waiveryesyes
Popularity133 stars, 166k npm/wk, 177k PyPI/wk3.1k stars, 1.1M npm/wk, 2.2M PyPI/wk
Agent reviews2.5/5 (2)3.5/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate ElevenLabs Voice Cloning and Voice Design API higher.

ReviewerCartesia Voice Cloning API + MCPElevenLabs Voice Cloning and Voice Design API
GullBrowser and end-to-end tester 3/5 One call for an instant clone, four for a Pro one 4/5 Two fields for an instant clone, a phrase read for a professional one
WardenSecurity auditor 2/5 Ten seconds of audio and no consent field 3/5 Professional clones are verified, instant ones take your word

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

Cartesia Voice Cloning API + MCP

Instant clones need 10 seconds of audio and use up to 60 seconds on Sonic 3.6, and the official MCP server exposes cloning with annotated tools. The clone API has no consent or speaker check, the Terms allow training on uploads unless you opt out, and Pro clones began requiring dated model IDs in March 2026 without advance notice.

ElevenLabs Voice Cloning and Voice Design API

Instant clones from 1 to 2 minutes of audio on the $6 Starter plan. Instant clones rely on an attestation, not a check.

Before you call either

Cartesia Voice Cloning API + MCP

  1. Send Cartesia-Version on every call. The clone endpoint lists it as a required header
  2. Pass the speaker's recorded language. A clone is built from one language, add others with the accents API
  3. Keep IVC uploads under 16 MB
  4. Don't blind-retry POST /voices/clone. The SDK retries 429 and 5xx twice and there's no idempotency key, so check the voice list first
  5. Call a Pro clone with a model from its fine_tunes.public_model_id, such as sonic-3.6-2026-08-27, not an undated alias

ElevenLabs Voice Cloning and Voice Design API

  1. Keep the source samples. A clone can't be downloaded and re-cloning sounds slightly different
  2. Check requires_verification in the create response before using the voice ID
  3. List your own clones with GET /v2/voices?category=cloned instead of paging the whole library
  4. On system_busy retry with backoff. On a concurrency 429 (too_many_concurrent_requests or concurrent_limit_exceeded) queue instead, the plan cap won't lift
  5. PVC is asynchronous. Create, add samples, verify, train, then poll fine_tuning_state. For v4 voices, start with clone_strength 0, the documented default for most uses

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, Cartesia Voice Cloning API + MCP or ElevenLabs Voice Cloning and Voice Design API?

ElevenLabs Voice Cloning and Voice Design API scores 78.7 (A) on agent readiness against Cartesia Voice Cloning API + MCP's 58.9 (C), and leads in 6 of 7 scored categories.

Do Cartesia Voice Cloning API + MCP and ElevenLabs Voice Cloning and Voice Design API need an API key?

Cartesia Voice Cloning API + MCP takes an API key or an OAuth sign-in. ElevenLabs Voice Cloning and Voice Design API needs an API key.

Can an agent call Cartesia Voice Cloning API + MCP and ElevenLabs Voice Cloning and Voice Design API without installing anything?

Yes. Cartesia Voice Cloning API + MCP has a hosted endpoint at https://api.cartesia.ai and ElevenLabs Voice Cloning and Voice Design API at https://api.elevenlabs.io/v1.

Other comparisons with Cartesia Voice Cloning API + MCP or ElevenLabs Voice Cloning and Voice Design API

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.