Cartesia website screenshot

Cartesia

Cartesia is a real-time multimodal AI platform built around the Sonic family of ultra-low-latency text-to-speech models and the Ink streaming speech-to-text models. Sonic models deliver the first audio byte in as little as 90ms, support more than 40 languages, and can express laughter and emotion, making them well-suited to conversational AI, voice agents, dubbing, and avatar applications. Ink models add streaming transcription with native turn detection optimized for voice agents. Cartesia ships Python, JavaScript, and Go SDKs and exposes REST, server-sent events, and WebSocket interfaces for streaming audio. The platform is SOC 2 Type II, HIPAA, and PCI Level 1 aligned.

Cartesia publishes 6 APIs on the APIs.io network, including Sonic Text-to-Speech API, Ink Speech-to-Text API, Auth API, and 3 more. Tagged areas include Voice, TTS, Text to Speech, STT, and Speech to Text.

The Cartesia catalog on APIs.io includes 1 event-driven AsyncAPI specification and 1 Spectral governance ruleset.

Cartesia’s developer surface includes authentication, documentation, engineering blog, pricing, and 10 more developer resources.

45.6/100 developing ▼ -6.9 Agent 36/100 agent ready Full breakdown ↓
scored 2026-07-28 · rubric v0.6
AccessFreeSelf serve⚡ Free to try
6 APIs
VoiceTTSText to SpeechSTTSpeech to TextStreamingWebSocketVoice AgentsVoice CloneSonicInkReal-Time

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-28 · rubric v0.6
Composite quality — 45.6/100 · developing
Contract Quality 16.4 / 25
Developer Ergonomics 4.3 / 20
Commercial Clarity 12.1 / 20
Operational Transparency 3.4 / 13
Governance 5.0 / 12
Discoverability 7.4 / 10
Agent readiness — 36/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 6 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/cartesia: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 6

Individual APIs this provider publishes, each with its own machine-readable definition.

Cartesia Sonic Text-to-Speech API

The Sonic text-to-speech API converts text into ultra-low-latency, emotive speech with sub-100ms time-to-first-byte. It supports REST, server-sent events, and WebSocket streamin...

Cartesia Ink Speech-to-Text API

The Ink streaming speech-to-text API transcribes audio in real time with native turn detection tuned for voice agents and conversational systems.

Cartesia Auth API

The Auth API from Cartesia — 1 operation(s) for auth.

Cartesia STT API

The STT API from Cartesia — 1 operation(s) for stt.

Cartesia TTS API

The TTS API from Cartesia — 2 operation(s) for tts.

Cartesia Voices API

The Voices API from Cartesia — 4 operation(s) for voices.

Open Collections 1

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

Cartesia API

OPEN COLLECTION

GraphQL 1

GraphQL schemas published by this provider.

Cartesia GraphQL Schema

This document describes a conceptual GraphQL schema for the Cartesia real-time text-to-speech and voice cloning API. Cartesia's native interfaces are REST, server-sent events, a...

GRAPHQL

Pricing Plans 1

Published pricing tiers and plan structures.

Rate Limits 1

Documented rate limits and quota policies.

Cartesia Rate Limits

2 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Cartesia Streaming WebSocket APIs

AsyncAPI description of Cartesia's real-time WebSocket interfaces, derived strictly from the official Cartesia documentation at https://docs.cartesia.ai. Three WebSocket surface...

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Cartesia API Rules

9 rules · 1 errors 8 warnings

SPECTRAL

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Cartesia Authentication

apiKey/http · 2 schemes

SECURITY

Cartesia Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Cartesia Agentic Access

10 operations · 8 acting

10 operations · 8 acting

AGENTIC

Resources

Documentation 1

Reference material describing how the API behaves

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

Build 1

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 1

Status, limits, changes, and where to get help

Commercial 3

Pricing, plans, and the legal terms of use

Company 3

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: cartesia
name: Cartesia
description: Cartesia is a real-time multimodal AI platform built around the Sonic family of ultra-low-latency text-to-speech
  models and the Ink streaming speech-to-text models. Sonic models deliver the first audio byte in as little as 90ms, support
  more than 40 languages, and can express laughter and emotion, making them well-suited to conversational AI, voice agents,
  dubbing, and avatar applications. Ink models add streaming transcription with native turn detection optimized for voice
  agents. Cartesia ships Python, JavaScript, and Go SDKs and exposes REST, server-sent events, and WebSocket interfaces for
  streaming audio. The platform is SOC 2 Type II, HIPAA, and PCI Level 1 aligned.
type: Index
accessModel:
  pricing: free
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Free · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
position: Provider
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/cartesia.png
tags:
- Voice
- TTS
- Text to Speech
- STT
- Speech to Text
- Streaming
- WebSocket
- Voice Agents
- Voice Clone
- Sonic
- Ink
- Real-Time
url: https://raw.githubusercontent.com/api-evangelist/cartesia/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-05-29'
specificationVersion: '0.20'
apis:
- aid: cartesia:tts-api
  name: Cartesia Sonic Text-to-Speech API
  description: The Sonic text-to-speech API converts text into ultra-low-latency, emotive speech with sub-100ms time-to-first-byte.
    It supports REST, server-sent events, and WebSocket streaming for real-time voice agents and applications.
  humanURL: https://docs.cartesia.ai
  baseURL: https://api.cartesia.ai
  tags:
  - TTS
  - Streaming
  - SSE
  - WebSocket
  - Real-Time
  - Voice
  properties:
  - type: Documentation
    url: https://docs.cartesia.ai
  - type: GettingStarted
    url: https://docs.cartesia.ai/get-started
  - type: Signup
    url: https://play.cartesia.ai
  - type: APIReference
    url: https://docs.cartesia.ai/api-reference
  - type: AsyncAPI
    url: https://raw.githubusercontent.com/api-evangelist/cartesia/refs/heads/main/asyncapi/cartesia-asyncapi.yml
  - type: SDKs
    url: https://github.com/cartesia-ai/cartesia-python
  - type: SDKs
    url: https://github.com/cartesia-ai/cartesia-js
  - type: SDKs
    url: https://github.com/cartesia-ai/cartesia-go
  - type: GitHubRepository
    url: https://github.com/cartesia-ai
  - type: Pricing
    url: https://cartesia.ai/pricing
  - type: Authentication
    url: https://docs.cartesia.ai
  - url: graphql/cartesia-graphql.md
    type: GraphQL
  features:
  - name: Ultra-Low Latency
    description: First audio byte in as little as 90ms for real-time conversational agents.
  - name: Multilingual
    description: More than 40 languages covering most major markets.
  - name: Emotive Speech
    description: Expressive prosody including laughter and emotion control.
  - name: Streaming Outputs
    description: REST, server-sent events, and WebSocket interfaces for streaming audio.
  - name: Voice Library
    description: Catalog of prebuilt voices accessible by ID across languages.
  - name: Instant Voice Clone
    description: Create a voice from a short reference clip for fast iteration.
  - name: Professional Voice Clone
    description: Higher-fidelity voice cloning for production avatars and brands.
  - name: Voice Localization
    description: Localize cloned and library voices into target languages.
  useCases:
  - name: Voice Agents
    description: Build low-latency conversational voice agents for support and sales.
  - name: Dubbing and Localization
    description: Dub video and audio into additional languages with voice continuity.
  - name: Interactive Characters
    description: Voice game characters, avatars, and interactive narration.
  - name: Accessibility
    description: Provide spoken interfaces and read-aloud features for accessibility.
  - name: Healthcare and IVR
    description: Power compliant voice experiences in healthcare and IVR systems.
  integrations:
  - name: LiveKit
  - name: Pipecat
  - name: Vapi
  - name: LangChain
  - name: LlamaIndex
  - name: Twilio
  - name: Daily
  - name: Vercel AI SDK
  - name: Retell
  - name: Bland
  authentication:
  - type: API Key
    description: API key authentication via the X-API-Key header alongside the Cartesia-Version header.
- aid: cartesia:stt-api
  name: Cartesia Ink Speech-to-Text API
  description: The Ink streaming speech-to-text API transcribes audio in real time with native turn detection tuned for voice
    agents and conversational systems.
  humanURL: https://docs.cartesia.ai
  baseURL: https://api.cartesia.ai
  tags:
  - STT
  - Streaming
  - Turn Detection
  - Voice Agents
  - WebSocket
  properties:
  - type: Documentation
    url: https://docs.cartesia.ai
  - type: APIReference
    url: https://docs.cartesia.ai/api-reference
  - type: AsyncAPI
    url: https://raw.githubusercontent.com/api-evangelist/cartesia/refs/heads/main/asyncapi/cartesia-asyncapi.yml
  - type: SDKs
    url: https://github.com/cartesia-ai/cartesia-python
  - type: SDKs
    url: https://github.com/cartesia-ai/cartesia-js
  - type: Pricing
    url: https://cartesia.ai/pricing
  features:
  - name: Streaming Transcription
    description: Real-time transcription of audio streams over WebSocket.
  - name: Turn Detection
    description: Native turn detection to decide when users finish speaking.
  - name: Voice Agent Optimization
    description: Tuned specifically for voice agent loops and barge-in handling.
  useCases:
  - name: Voice Agent Listening
    description: Provide low-latency listening for voice agent stacks.
  - name: Live Captioning
    description: Generate live captions for meetings and broadcasts.
  - name: Voice Form Capture
    description: Capture structured input from voice in real time.
  integrations:
  - name: LiveKit
  - name: Pipecat
  - name: Daily
  - name: Twilio
  authentication:
  - type: API Key
    description: API key authentication via the X-API-Key header alongside the Cartesia-Version header.
- aid: cartesia:cartesia-auth-api
  name: Cartesia Auth API
  description: The Auth API from Cartesia — 1 operation(s) for auth.
  humanURL: https://docs.cartesia.ai
  baseURL: https://api.cartesia.ai
  tags:
  - Auth
  properties:
  - type: OpenAPI
    url: openapi/cartesia-auth-api-openapi.yml
- aid: cartesia:cartesia-stt-api
  name: Cartesia STT API
  description: The STT API from Cartesia — 1 operation(s) for stt.
  humanURL: https://docs.cartesia.ai
  baseURL: https://api.cartesia.ai
  tags:
  - STT
  properties:
  - type: OpenAPI
    url: openapi/cartesia-stt-api-openapi.yml
- aid: cartesia:cartesia-tts-api
  name: Cartesia TTS API
  description: The TTS API from Cartesia — 2 operation(s) for tts.
  humanURL: https://docs.cartesia.ai
  baseURL: https://api.cartesia.ai
  tags:
  - TTS
  properties:
  - type: OpenAPI
    url: openapi/cartesia-tts-api-openapi.yml
- aid: cartesia:cartesia-voices-api
  name: Cartesia Voices API
  description: The Voices API from Cartesia — 4 operation(s) for voices.
  humanURL: https://docs.cartesia.ai
  baseURL: https://api.cartesia.ai
  tags:
  - Voices
  properties:
  - type: OpenAPI
    url: openapi/cartesia-voices-api-openapi.yml
common:
- type: AgenticAccess
  url: agentic-access/cartesia-agentic-access.yml
- type: DomainSecurity
  url: security/cartesia-domain-security.yml
- type: Authentication
  url: authentication/cartesia-authentication.yml
- type: Website
  url: https://cartesia.ai
- type: Documentation
  url: https://docs.cartesia.ai
- type: Blog
  url: https://cartesia.ai/blog
- type: GitHubOrganization
  url: https://github.com/cartesia-ai
- type: Pricing
  url: https://cartesia.ai/pricing
- type: TermsOfService
  url: https://cartesia.ai/legal/terms-of-service
- type: PrivacyPolicy
  url: https://cartesia.ai/legal/privacy-policy
- type: Discord
  url: https://discord.gg/cartesia
- type: X
  url: https://x.com/cartesia_ai
- type: LinkedIn
  url: https://www.linkedin.com/company/cartesia-ai
- type: LlmsText
  url: https://docs.cartesia.ai/llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com