> ## 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.

# Similarity

> Set how closely a HeyGen Voice instant clone follows its source recording with similarity in POST /v3/models/audio/voices.

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

`similarity` sets how closely an [instant voice](https://developers.heygen.com/docs/voices/heygen-voice-instant-clone.md) follows the recording it was cloned from. Higher levels keep more of the speaker's character, and more of the recording's room sound. Lower levels give the voice more room to adapt its delivery. You set it once, when you create the clone with [`POST /v3/models/audio/voices`](https://developers.heygen.com/reference/create-or-retrain-an-audio-voice).

| `similarity` | |
| - | - |
| `medium` | Loosest match. |
| `high` | |
| `extra_high` | Default. |
| `max` | Closest match. |

## Listen

One 45-second recording, cloned four times with a different `similarity` each time. All four clones speak the same script with `heygen-voice-1`, in English, with `expressiveness_boost: 0`.

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

> Welcome back. Today, we will walk through your project settings, review the latest changes, and make sure everything is ready before you share your next video.

> [card] medium
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/similarity/medium.mp3" />

> [card] high
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/similarity/high.mp3" />

> [card] extra\_high
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/similarity/extra-high.mp3" />

> [card] max
>
> <audio controls preload="none" src="https://developers.heygen.com/images/heygen-voice/similarity/max.mp3" />

Listen for vocal character, phrasing, and how much of the room comes through.

## Create a clone at a level

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

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).

An instant voice keeps the level it was created with. To hear another level, create a new clone from the same recording; each clone has its own `voice_id`.

## Tips

* Record in a quiet room without echo. `extra_high` and `max` keep more of the recording's room sound than `medium`.
* To compare levels, keep the recording, text, language, and `remove_background_noise` the same, and send the same `expressiveness_boost` in every speech request. Try a few short passages.
* For the closest match to the original speaker, use `max` and send [`expressiveness_boost: 0.0`](https://developers.heygen.com/docs/voices/heygen-voice-expressiveness-boost).
* For HeyGen videos, our preferred combination is `max` with `expressiveness_boost: 0.5`.
* An [`image`](https://developers.heygen.com/docs/voices/heygen-voice-adaptive-image) of the speaker's setting changes the voice's ambience. Keep it the same, or leave it out, while you compare levels.


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