How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Cartesia Voices API

Voice catalog management and voice cloning.

Cartesia Voices API is one of 23 APIs that Cartesia publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Voices. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, and an API reference.

This API exposes 6 operations across 4 paths, and defines 4 schemas. It is described by OpenAPI 3.2.0, at version 2026-03-01.

Requests are made against a single base URL, https://api.cartesia.ai.

6 operations 4 paths 4 schemas 1 DELETE2 GET1 PATCH2 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
2026-03-01
Base URL
https://api.cartesia.ai
Authentication
HTTP Bearer
Contact
Resource Areas
1

Authentication & Security 1

Cartesia Voices API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (sk_car_... API key or short-lived access token) (bearerAuth). By default, every request must be authenticated.

  • bearerAuth — Cartesia API key (skcar...) or a short-lived access token minted via POST /access-token, passed as Authorization: Bearer . Every request also requires the Cart…

Paths & Operations 6

Across 4 paths, the API surfaces 6 operations — 1 DELETE, 2 GET, 1 PATCH, 2 POST. Each is listed below with its method, path, parameters, and response codes.

Voices 6

Voice catalog management and voice cloning.

GET
/voices
List Voices
listVoices 9 params → 200401
POST
/voices/clone
Clone Voice
cloneVoice 1 param body → 200401422
GET
/voices/{id}
Get Voice
getVoice 2 params → 200401404
PATCH
/voices/{id}
Update Voice
updateVoice 2 params body → 200401404
DELETE
/voices/{id}
Delete Voice
deleteVoice 2 params → 200401404
POST
/voices/localize
Localize Voice
localizeVoice 1 param body → 200401422

Schemas 4

The contract defines 4 schemas that model the data the API accepts and returns. The most detailed are VoiceMetadata (11 properties), Error (6 properties), GetVoicesResponse (3 properties), DeleteResponse (2 properties). Each schema is shown below with its type and property counts.

VoiceMetadata
object
11 properties
DeleteResponse
object
2 properties
GetVoicesResponse
object
3 properties
Error
object
6 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

cartesia-ai-voices-api-openapi.yml Raw ↑

Other APIs Cartesia publishes across the network.

Cartesia TTS WebSocket API
Cartesia STT WebSocket API
Cartesia Agents API
Cartesia API Keys API
Cartesia Auth API
Cartesia Calls API
Cartesia Datasets API
Cartesia Deployments API
Cartesia Infill API
Cartesia Knowledge Base API
Cartesia Metrics API
Cartesia Phone Numbers API
Where this information came from

This is an independent, third-party profile of Cartesia Voices API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.