aid: cartesia-ai
url: https://raw.githubusercontent.com/api-evangelist/cartesia-ai/refs/heads/main/apis.yml
name: Cartesia
kind: company
description: Cartesia builds real-time voice AI - the Sonic family of text-to-speech
  models, Ink speech-to-text models, and a Voice Agents platform for building and
  deploying telephone and web voice agents. The core generation surface is exposed
  both as REST (bytes and Server-Sent Events) and as a low-latency, bidirectional
  WebSocket protocol at wss://api.cartesia.ai for streaming TTS and STT with
  multiplexed contexts, word/phoneme timestamps, and mid-stream flush and cancel.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- Voice AI
- Text to Speech
- Speech to Text
- Realtime
- WebSocket
- Voice Cloning
- Voice Agents
created: '2026-07-02'
modified: '2026-07-02'
specificationVersion: '0.19'
apis:
- aid: cartesia-ai:cartesia-ai-text-to-speech-api
  name: Cartesia Text-to-Speech API
  tags:
  - Text to Speech
  - Sonic
  - Audio
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/tts/bytes
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/build-with-cartesia/tts-models/latest
    type: Documentation
  - url: https://docs.cartesia.ai/api-reference/tts/bytes
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Synthesize speech from text with the Sonic model family (sonic-3.5,
    sonic-3, sonic-latest) over plain HTTP - a single-shot binary response at
    POST /tts/bytes or a Server-Sent Events stream with per-chunk metadata at
    POST /tts/sse. Supports 40+ languages, raw/wav/mp3 output formats, and
    generation controls for volume, speed, and emotion.
- aid: cartesia-ai:cartesia-ai-tts-websocket-api
  name: Cartesia TTS WebSocket API
  tags:
  - WebSocket
  - Text to Speech
  - Realtime
  - Streaming
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/tts/websocket
  baseURL: wss://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/tts/websocket
    type: Documentation
  - url: asyncapi/cartesia-ai-asyncapi.yml
    type: AsyncAPI
  description: Bidirectional, multiplexed WebSocket at wss://api.cartesia.ai/tts/websocket
    for realtime speech generation. Clients send JSON generation requests keyed
    by a context_id (continuing a context preserves prosody across chunks of
    transcript) and receive base64-encoded audio chunks, optional word and
    phoneme timestamps, flush acknowledgements, and a final done message. A
    single connection scales to dozens of concurrent generation contexts.
- aid: cartesia-ai:cartesia-ai-speech-to-text-api
  name: Cartesia Speech-to-Text API
  tags:
  - Speech to Text
  - Transcription
  - Ink Whisper
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/stt/transcribe
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/build-with-cartesia/stt/latest
    type: Documentation
  - url: https://docs.cartesia.ai/api-reference/stt/transcribe
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Batch transcription of an audio file of any length with the
    ink-whisper model at POST /stt. Accepts flac, m4a, mp3, mp4, and mpeg
    uploads, 99+ languages, and optional word-level timestamp granularity.
- aid: cartesia-ai:cartesia-ai-stt-websocket-api
  name: Cartesia STT WebSocket API
  tags:
  - WebSocket
  - Speech to Text
  - Realtime
  - Turn Detection
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/stt/websocket
  baseURL: wss://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/stt/turns/websocket
    type: Documentation
  - url: https://docs.cartesia.ai/api-reference/stt/websocket
    type: APIReference
  - url: asyncapi/cartesia-ai-asyncapi.yml
    type: AsyncAPI
  description: Realtime transcription over WebSocket at wss://api.cartesia.ai/stt/websocket.
    Clients stream raw binary audio in 100ms chunks and issue finalize/close
    text commands; the server returns incremental and final transcript
    messages with word-level timing. A companion "Auto" variant at
    /stt/turns/websocket adds built-in turn detection for conversational
    agents.
- aid: cartesia-ai:cartesia-ai-voices-api
  name: Cartesia Voices API
  tags:
  - Voices
  - Voice Cloning
  - Localization
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/voices/list
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/voices/list
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Manage the voice catalog - list, search, and filter voices by
    gender, language, and ownership; get, update, and delete a voice; clone a
    new voice from an uploaded audio clip at POST /voices/clone; and localize
    an existing voice into a new language and dialect at POST /voices/localize.
- aid: cartesia-ai:cartesia-ai-voice-changer-api
  name: Cartesia Voice Changer API
  tags:
  - Voice Changer
  - Audio
  - Speech to Speech
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/voice-changer/bytes
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/voice-changer/bytes
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Transform an input speech recording into a different target
    voice - a single-shot binary response at POST /voice-changer/bytes or a
    Server-Sent Events stream at POST /voice-changer/sse.
- aid: cartesia-ai:cartesia-ai-infill-api
  name: Cartesia Infill API
  tags:
  - Infill
  - Audio Editing
  - Sonic
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/infill/bytes
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/infill/bytes
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Generate audio that smoothly connects two existing audio
    segments at POST /infill/bytes - supply a left and/or right audio clip
    plus the transcript to be spoken between them, useful for fixing or
    extending existing voice recordings without a full re-record.
- aid: cartesia-ai:cartesia-ai-datasets-api
  name: Cartesia Datasets API
  tags:
  - Datasets
  - Fine-Tuning
  - Files
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/datasets/list
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/datasets/list
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Create, list, get, update, and delete datasets, and upload,
    list, and delete files within a dataset - the audio/text collections used
    to build custom fine-tunes and voices.
- aid: cartesia-ai:cartesia-ai-pronunciation-dictionaries-api
  name: Cartesia Pronunciation Dictionaries API
  tags:
  - Pronunciation
  - Dictionaries
  - Text to Speech
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/pronunciation-dicts/list
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/pronunciation-dicts/list
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Create, list, get, update, and delete custom pronunciation
    dictionaries that can be referenced by pronunciation_dict_id on TTS
    requests to override how specific words or terms are spoken.
- aid: cartesia-ai:cartesia-ai-api-keys-auth-api
  name: Cartesia API Keys and Auth API
  tags:
  - API Keys
  - Authentication
  - Access Tokens
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/api-keys/list
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/api-keys/list
    type: APIReference
  - url: https://docs.cartesia.ai/api-reference/auth/access-token
    type: Documentation
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: List and get metadata for standard API keys, and mint
    short-lived (up to 3600s) scoped access tokens at POST /access-token with
    tts/stt/agent grants for safe use in browser and client-side contexts.
- aid: cartesia-ai:cartesia-ai-voice-agents-api
  name: Cartesia Voice Agents API
  tags:
  - Voice Agents
  - Telephony
  - Calls
  - Knowledge Base
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/agents/agents/list
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/agents/agents/list
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Build and operate voice agents end to end - manage agents and
    public templates; place, list, cancel, and batch outbound calls and
    download call audio and logs; import, provision, and manage telephony
    phone numbers and provider accounts; register webhooks; inspect
    deployments; and maintain a knowledge base of documents and folders plus
    LLM-as-a-judge metrics used to evaluate agent quality.
- aid: cartesia-ai:cartesia-ai-usage-api
  name: Cartesia Usage API
  tags:
  - Usage
  - Credits
  - Billing
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.cartesia.ai/api-reference/usage/credits
  baseURL: https://api.cartesia.ai
  properties:
  - url: https://docs.cartesia.ai/api-reference/usage/credits
    type: APIReference
  - url: https://docs.cartesia.ai/api-reference/usage/agents
    type: APIReference
  - url: openapi/cartesia-ai-openapi.yml
    type: OpenAPI
  description: Read-only usage endpoints returning credit consumption and
    agent usage over time, bucketed by the requested interval, for
    monitoring spend against a plan's included credits.
common:
- type: DomainSecurity
  url: security/cartesia-ai-domain-security.yml
- type: Authentication
  url: authentication/cartesia-ai-authentication.yml
- url: https://cartesia.ai/blog
  type: Blog
- type: GitHubOrganization
  url: https://github.com/cartesia-ai
- type: LinkedIn
  url: https://www.linkedin.com/company/cartesia-ai
- type: Website
  url: https://cartesia.ai/
- type: Documentation
  url: https://docs.cartesia.ai
- type: Plans
  url: plans/cartesia-ai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/cartesia-ai-rate-limits.yml
- type: FinOps
  url: finops/cartesia-ai-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com