> ## 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.

# Deprecated Models

## Upcoming sunsets

| Model         | Snapshots affected   | Sunset date      |
| ------------- | -------------------- | ---------------- |
| `sonic-2`     | All                  | October 20, 2026 |
| `sonic-turbo` | All                  | October 20, 2026 |
| `sonic-3`     | `sonic-3-2025-10-27` | October 20, 2026 |

## Sunsetted models

Requests to sunsetted models will return an error. See this example error response:

```json theme={null}
{
  "error_code": "model_sunsetted",
  "message": "The requested model has been sunsetted and is no longer available.",
  "title": "Model sunsetted",
  "request_id": "897525c5-7bbe-4919-a801-95170b472373"
}
```

| Model                | Snapshots affected                                               | Sunsetted languages        | Sunset date  |
| -------------------- | ---------------------------------------------------------------- | -------------------------- | ------------ |
| `sonic`              | All                                                              | All                        | June 1, 2026 |
| `sonic-english`      | —                                                                | All                        | June 1, 2026 |
| `sonic-multilingual` | —                                                                | All                        | June 1, 2026 |
| `sonic-2`            | `sonic-2-2025-03-07`                                             | All                        | June 1, 2026 |
| `sonic-2`            | `sonic-2-2025-04-16`, `sonic-2-2025-05-08`, `sonic-2-2025-06-11` | it, nl, pl, ru, sv, tr, hi | June 1, 2026 |
| `sonic-turbo`        | `sonic-turbo-2025-03-07`                                         | All                        | June 1, 2026 |
| `sonic-turbo`        | `sonic-turbo-2025-06-04`                                         | it, nl, pl, ru, sv, tr     | June 1, 2026 |

## Stable offerings

| Model           | Snapshots              | Supported Languages                                                                        |
| --------------- | ---------------------- | ------------------------------------------------------------------------------------------ |
| `sonic-preview` | Sonic 3.6 preview      | 44 languages — [per-snapshot list](/build-with-cartesia/tts-models/latest#model-snapshots) |
| `sonic-3.5`     | `sonic-3.5-2026-05-04` | 42 languages — [per-snapshot list](/build-with-cartesia/tts-models/latest#model-snapshots) |
| `sonic-3`       | `sonic-3-2026-01-12`   | 42 languages — [full list](/build-with-cartesia/tts-models/older-models#sonic-3)           |

## Breaking API changes

These endpoints are being sunset. Requests after an endpoint's sunset date return an error.

| Breaking                                                                                 | Replacement                                                      | Sunset date     |
| ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------- | --------------- |
| Voice Embedding: `POST /voices/clone/clip`                                               | [Clone Voice](/api-reference/voices/clone): `POST /voices/clone` | June 1, 2026    |
| [Mix Voices](/2024-11-13/api-reference/voices/mix): `POST /voices/mix`                   | —                                                                | June 1, 2026    |
| [Create Voice](/2024-11-13/api-reference/voices/create): `POST /voices`                  | [Clone Voice](/api-reference/voices/clone): `POST /voices/clone` | June 1, 2026    |
| [Voice Changer (Bytes)](/api-reference/voice-changer/bytes): `POST /voice-changer/bytes` | —                                                                | August 20, 2026 |
| [Voice Changer (SSE)](/api-reference/voice-changer/sse): `POST /voice-changer/sse`       | —                                                                | August 20, 2026 |

These endpoints stopped accepting voice embeddings on June 1, 2026.

| Endpoint                                                          | Breaking                       | Replacement             |
| ----------------------------------------------------------------- | ------------------------------ | ----------------------- |
| [TTS (bytes)](/api-reference/tts/bytes): `POST /tts/bytes`        | `"voice":{"mode":"embedding"}` | `"voice": "<voice-id>"` |
| [TTS (SSE)](/api-reference/tts/sse): `POST /tts/sse`              | `"voice":{"mode":"embedding"}` | `"voice": "<voice-id>"` |
| [TTS (WebSocket)](/api-reference/tts/websocket): `/tts/websocket` | `"voice":{"mode":"embedding"}` | `"voice": "<voice-id>"` |

### API Migration Guides

<AccordionGroup>
  <Accordion title="Creating voices">
    You can move to our [Clone Voice API](/api-reference/voices/clone) or use our [web UI](https://play.cartesia.ai/voices/create/clone) to create voices from 3–10 seconds of source audio.

    Here is an example using the Cartesia SDK:

    ```python theme={null}
    your_api_key: str = ""

    client = Cartesia(api_key=your_api_key)

    print("Cloning a voice")
    with open("3 to 10 seconds of source audio.wav", mode="rb") as f:
        voice = client.voices.clone(
            clip=f,
            # this must match the source audio
            language="en",
            name="My Voice",
            mode="similarity",
    )
    print(f"Cloned voice {voice.id}")

    print("Generating audio...")
    generated_audio = client.tts.generate(
        # voice embeddings will not work after June 1, 2026!
        voice=voice.id,
        model_id="sonic-3.5",
        transcript="Hello from Cartesia!",
        language="en",
        output_format={
            "container": "wav",
            "encoding": "pcm_f32le",
            "sample_rate": 44100
        },
    )
    ```
  </Accordion>

  <Accordion title="Voice IDs">
    If you are currently making generation requests with voice embeddings like this:

    ```json theme={null}
    {
      "voice": {
        "mode": "embedding",
        "embedding": [1, 2, ..., 3, 4]
      },
      "model_id": "sonic-2",
      // ...
    }
    ```

    You will need to switch to using voice IDs like this:

    ```json theme={null}
    {
      "voice": "e07c00bc-4134-4eae-9ea4-1a55fb45746b",
      "model_id": "sonic-2",
      // ...
    }
    ```

    #### Don't have a voice ID?

    ##### Check out the voice library

    Our featured voices have all gone through rigorous evaluations and are ready to use in production.

    Check them out at [play.cartesia.ai/voices](https://play.cartesia.ai/voices) and copy the ID of any voice you'd like to use.

    ##### Clone a voice

    If you have source audio, create a cloned voice via the [playground](https://play.cartesia.ai/voices/create/clone) or the [API](/api-reference/voices/clone). Cloning returns a voice ID you can use immediately.
  </Accordion>
</AccordionGroup>