Cartesia · GraphQL Specification

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, and WebSocket; this schema models those capabilities as a GraphQL surface to support tooling, federation, and developer exploration.

Documentation Endpoint View on GitHub VoiceTTSText to SpeechSTTSpeech to TextStreamingWebSocketVoice AgentsVoice CloneSonicInkReal-TimeGraphQL

Overview

Cartesia GraphQL Schema is a GraphQL API specification published by Cartesia on the APIs.io network.

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, and WebSocket; this schema models those capabilities as a GraphQL surface to support tooling, federation, and developer exploration.

The specification includes 3 reference links.

Tagged areas include Voice, TTS, Text to Speech, STT, and Speech to Text.

Endpoint

References

Related API Specs

Cartesia Sonic Text-to-Speech API (AsyncAPI) Cartesia Ink Speech-to-Text API (AsyncAPI) Cartesia Auth API (OpenAPI) Cartesia STT API (OpenAPI) Cartesia TTS API (OpenAPI) Cartesia Voices API (OpenAPI)
Back to Cartesia · All GraphQL Specs · GitHub