ModelInfo
English
All models

Ink 2

Cartesia streaming speech-to-text model for voice agents with built-in turn detection, supporting English, French, Hindi, Japanese and Spanish.

Cartesiaink-22026-09-17Report incorrect data

Specs

Context
—
Max output
—
Input price
—
Output price
—
Released
2026-09-17

Context

Not published

Pricing

Not published

Modalities

Input
Audio
Output
Text

API

API types
audiorealtime

Reasoning

Not published

Info

Status
Active
Released
2026-09-17
Knowledge cutoff
—

Features

Not published
Source · official docsVerified 2026-10-11

How to call

1 provider

cartesiamodel = ink-2

audio
POSThttps://api.cartesia.ai/stt
realtime
GEThttps://api.cartesia.ai/stt/websocket

JSON

Standard format
ink-2.json
{
  "id": "ink-2",
  "object": "model",
  "created": 1789603200,
  "owned_by": "cartesia",
  "name": "Ink 2",
  "api": {
    "types": [
      "audio",
      "realtime"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "audio"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": null,
  "features": [],
  "info": {
    "status": "active",
    "release_date": "2026-09-17",
    "knowledge_cutoff": null,
    "description": "Cartesia streaming speech-to-text model for voice agents with built-in turn detection, supporting English, French, Hindi, Japanese and Spanish.",
    "docs": "https://docs.cartesia.ai/build-with-cartesia/stt-models",
    "verified_at": "2026-10-11"
  }
}

Official sources

1