> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cartesia.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Ink 2

Ink 2 is our fastest, most accurate streaming speech-to-text model — the lowest word error rate and best turn detection of any streaming STT, built for production voice agents. It transcribes structured data like phone numbers, dates, and emails right the first time, and knows when a speaker starts and finishes — no separate VAD required.

Turn detection is built in. Ink 2 emits a full lifecycle of turn events — `turn.start`, `turn.update`, `turn.eager_end`, `turn.resume`, and `turn.end` — so your agent knows exactly when to listen, think, and respond. See [Turn Events](/use-the-api/stt/turns/turns) for the state machine, or [Compare STT Endpoints](/use-the-api/compare-stt-endpoints) to run Ink 2 with or without turn detection.

## Models

| Model   | Release Date | Languages | Status  |
| ------- | ------------ | --------- | ------- |
| `ink-2` | May 22, 2026 | `en`      | Preview |

For information on `ink-whisper`, see our page on [Older STT Models](/build-with-cartesia/stt-models/older-models).

## Where to go next

<CardGroup cols={3}>
  <Card title="Understand turn detection" icon="comments" href="/use-the-api/stt/turns/turns">
    See how user turn events work in voice agents
  </Card>

  <Card title="Try it out online" icon="arrow-pointer" href="https://www.cartesia.ai/ink">
    Test out Ink 2 with no sign-up or code required
  </Card>

  <Card title="Use the API" icon="code" href="/api-reference/stt/turns/websocket">
    Start building with our Realtime STT API
  </Card>

  <Card title="Use the SDK" icon="brackets-curly" href="/examples/stt-auto-finalize-websocket">
    Take a look at some real code
  </Card>

  <Card title="Integrations" icon="plug" href="/integrations/overview">
    LiveKit, Pipecat, and other voice agent builders
  </Card>

  <Card title="Migrate from Deepgram Flux" href="/use-the-api/stt/turns/migrate-from-deepgram-flux" icon="arrows-left-right">
    Deepgram's turn-based audio
  </Card>
</CardGroup>