Cartesia STT API

openapi: 3.1.0
info:
  title: Cartesia Auth STT API
  description: Cartesia is a real-time multimodal AI platform built around the Sonic text-to-speech and Ink streaming speech-to-text models. The REST API supports synchronous and streaming generation, voice management, voice cloning, and access-token issuance.
  version: '2024-11-13'
  contact:
    name: Cartesia
    url: https://docs.cartesia.ai
servers:
- url: https://api.cartesia.ai
  description: Production
security:
- ApiKeyAuth: []
- BearerAuth: []
tags:
- name: STT
paths:
  /stt/transcribe:
    post:
      tags:
      - STT
      summary: Batch transcribe audio with the Ink model
      operationId: sttTranscribe
      parameters:
      - $ref: '#/components/parameters/CartesiaVersion'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - file
              - model
              properties:
                file:
                  type: string
                  format: binary
                model:
                  type: string
                language:
                  type: string
                timestamp_granularities:
                  type: array
                  items:
                    type: string
      responses:
        '200':
          description: Transcript
          content:
            application/json:
              schema:
                type: object
components:
  parameters:
    CartesiaVersion:
      in: header
      name: Cartesia-Version
      required: true
      schema:
        type: string
        example: '2024-11-13'
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: Cartesia API key (sk_car_...)
    BearerAuth:
      type: http
      scheme: bearer
      description: Short-lived client access token