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

# Adaptive Image

> Give a HeyGen Voice instant clone an image of the speaker in their setting, so the voice takes on that scene's acoustics and ambience.

![](https://mintcdn.com/heygen-1fa696a7/hfMXXwJzjE7vBSYZ/images/theme/research-2.webp?fit=max\&auto=format\&n=hfMXXwJzjE7vBSYZ\&q=85\&s=d6ee10585b27ddaf8137d6ed67791708)

Send an `image` of the speaker in their setting when you create an [instant voice](https://developers.heygen.com/docs/voices/heygen-voice-instant-clone.md), and the voice takes on the acoustics of that scene. A quiet studio keeps it clean; a beach or a factory floor adds matching ambience. The speaker's accent and phrasing stay the same.

## Listen

One recording, made in a meeting room:

> [card] Source recording
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/adaptive-image/original.mp3" />

The same voice in four scenes, each reading this line:

> Same voice, different scene. Listen to how it changes. Still sounds like me, right?

> [card] Studio
>
> ![Speaker in a recording studio](https://mintcdn.com/heygen-1fa696a7/XGnaF2uNPN4dZj2K/images/heygen-voice/adaptive-image/studio.webp?fit=max\&auto=format\&n=XGnaF2uNPN4dZj2K\&q=85\&s=eb6efd0afcaa554107df608ea5f25076)
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/adaptive-image/studio.mp3" />

> [card] Beach
>
> ![Speaker on a beach](https://mintcdn.com/heygen-1fa696a7/XGnaF2uNPN4dZj2K/images/heygen-voice/adaptive-image/beach.webp?fit=max\&auto=format\&n=XGnaF2uNPN4dZj2K\&q=85\&s=6f4b2e5853a5935335b3ee4314181cca)
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/adaptive-image/beach.mp3" />

> [card] Factory floor
>
> ![Speaker on a factory floor](https://mintcdn.com/heygen-1fa696a7/XGnaF2uNPN4dZj2K/images/heygen-voice/adaptive-image/factory.webp?fit=max\&auto=format\&n=XGnaF2uNPN4dZj2K\&q=85\&s=602a133d4eec7cbfabf513f265b7c5ca)
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/adaptive-image/factory.mp3" />

> [card] Car
>
> ![Speaker in a car](https://mintcdn.com/heygen-1fa696a7/XGnaF2uNPN4dZj2K/images/heygen-voice/adaptive-image/car.webp?fit=max\&auto=format\&n=XGnaF2uNPN4dZj2K\&q=85\&s=39ae0e73922741e1809f641d0f152b2a)
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/adaptive-image/car.mp3" />

Each still is a frame from that scene's video.

## Create a voice for a scene

[Upload](https://developers.heygen.com/docs/upload-assets.md) the recording and the scene image, then pass both to [`POST /v3/models/audio/voices`](https://developers.heygen.com/reference/create-or-retrain-an-audio-voice):

```bash theme={null}
curl -X POST "https://api.heygen.com/v3/models/audio/voices" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "instant",
    "name": "Narrator, studio",
    "language": "en",
    "audio": [
      { "type": "asset_id", "asset_id": "'"$AUDIO_ASSET_ID"'" }
    ],
    "image": { "type": "asset_id", "asset_id": "'"$IMAGE_ASSET_ID"'" }
  }'
```

Wait until the voice is [`ACTIVE`](https://developers.heygen.com/docs/voices/heygen-voice-instant-clone#2-wait-until-it-is-active), then pass its `voice_id` to [Text to Speech](https://developers.heygen.com/docs/voices/heygen-voice-speech.md). Every speech request with that voice uses the scene.

## The image

* A JPEG, PNG, or WebP that shows the speaker and their surroundings, as an `asset_id`, a public HTTPS `url`, or `base64`.
* Send `image` on its own, without `gender` or `age`. Without an image, HeyGen picks a default scene from the speaker's gender and age, detected from the recording or taken from those two fields.
* The scene is part of the voice. For another scene, create another clone from the same recording with a different `image`.

## Tips

* To compare scenes, keep the recording, [`similarity`](https://developers.heygen.com/docs/voices/heygen-voice-similarity), `remove_background_noise`, text, language, and [`expressiveness_boost`](https://developers.heygen.com/docs/voices/heygen-voice-expressiveness-boost) the same, and change only the image.
* Use a script that fits any setting, so the image is the only difference you hear.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.