> ## Documentation Index
> Fetch the complete documentation index at: https://heygen-1fa696a7.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> The models behind the HeyGen API: HeyGen Video for prompt-to-video, the Avatar 6, Avatar V, Avatar IV, and Avatar III rendering engines, HeyGen Voice for voice cloning and speech, and HeyGen Decision for classifying and scoring text, images, video, and audio.

![](https://mintcdn.com/heygen-1fa696a7/hfMXXwJzjE7vBSYZ/images/theme/research-3.webp?fit=max\&auto=format\&n=hfMXXwJzjE7vBSYZ\&q=85\&s=c8191ba4743fd85050f1af1a93ed4969)

> [card] [HeyGen Video](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-video.md)
>
> Prompt to video. Generates the whole frame.

> [card] [Avatar 6](https://heygen-1fa696a7.mintlify.site/docs/models/avatar-6.md)
>
> Newest avatar engine. Up to 2K.

> [card] [Avatar V](https://heygen-1fa696a7.mintlify.site/avatar-v.md)
>
> Highest fidelity. Opt-in per look.

> [card] [Avatar IV](https://heygen-1fa696a7.mintlify.site/avatar-iv.md)
>
> Default engine. Broadest coverage.

> [card] [Avatar III](https://heygen-1fa696a7.mintlify.site/avatar-iii.md)
>
> Photo-to-video pipeline. 4K.

> [card] [HeyGen Voice](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-voice.md)
>
> Voice clones and speech.

> [card] [HeyGen Decision](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-decision.md)
>
> Answers about text, images, and video.

The v3 API exposes four model families.

## HeyGen Video

**[HeyGen Video](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-video.md)** generates video from a prompt, inventing the subject, the setting and the sound together in one call to [`POST /v3/models/videos`](https://heygen-1fa696a7.mintlify.site/reference/create-heygen-video).

## HeyGen Avatar

Avatar rendering engines turn a look and a script into video, selected per request through the `engine` field on [`POST /v3/videos`](https://heygen-1fa696a7.mintlify.site/reference/create-video). New integrations should start with [Avatar 6](https://heygen-1fa696a7.mintlify.site/docs/models/avatar-6.md). [Avatar V](https://heygen-1fa696a7.mintlify.site/avatar-v.md) and [Avatar IV](https://heygen-1fa696a7.mintlify.site/avatar-iv.md) (the default when `engine` is omitted) cover looks outside Avatar 6, and [Avatar III](https://heygen-1fa696a7.mintlify.site/avatar-iii.md) runs a dedicated photo-to-video pipeline.

```json theme={null}
{
  "type": "avatar",
  "avatar_id": "YOUR_LOOK_ID",
  "script": "Hello from HeyGen.",
  "voice_id": "YOUR_VOICE_ID",
  "engine": { "type": "heygen-avatar-6" }
}
```

Before requesting an engine, confirm the look supports it: `supported_api_engines` on [`GET /v3/avatars/looks/{look_id}`](https://heygen-1fa696a7.mintlify.site/reference/get-avatar-look) lists which of `heygen-avatar-6`, `heygen-avatar-6-turbo`, `avatar_iii`, `avatar_iv`, and `avatar_v` the look accepts. Requesting an engine that isn't listed returns `400`.

| | [Avatar 6](https://heygen-1fa696a7.mintlify.site/docs/models/avatar-6.md) | [Avatar V](https://heygen-1fa696a7.mintlify.site/avatar-v.md) | [Avatar IV](https://heygen-1fa696a7.mintlify.site/avatar-iv.md) | [Avatar III](https://heygen-1fa696a7.mintlify.site/avatar-iii.md) |
| - | - | - | - | - |
| `engine.type` | `heygen-avatar-6`, `heygen-avatar-6-turbo` | `avatar_v` | `avatar_iv` | `avatar_iii` |
| API version | v3 | v3 | v3 | v3 |
| Default engine | Explicit opt-in | ✗ (explicit opt-in) | ✓ | ✗ (explicit opt-in) |
| Digital Twin | ✓ | ✓ | ✓ | ✓ |
| Photo Avatar | ✓ | ✓ | ✓ | ✓ (dedicated pipeline) |
| Studio Avatar | Eligible looks | ✓ | ✓ | ✓ (renders as Digital Twin) |
| Arbitrary image input | Through the [Model API](https://heygen-1fa696a7.mintlify.site/docs/models/avatar-6.md#model-api) | ✗ | ✓ | ✗ |
| `motion_prompt` | ✓ | ✓ | ✓ (photo avatars and images only) | ✗ |
| `expressiveness` | `engine.motion_expressiveness` | ✗ | ✓ (photo avatars and images only) | ✗ |
| Cross-reference animation | `engine.reference_look_id` | ✓ | ✗ | ✗ |
| Eligibility check required | ✓ | ✓ | ✗ | ✗ |

## HeyGen Voice

[HeyGen Voice](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-voice.md) is HeyGen's in-house voice model. Clone a speaker on `POST /v3/models/audio/voices` as an [`instant`](https://heygen-1fa696a7.mintlify.site/docs/voices/heygen-voice-instant-clone) voice from one recording, ready in seconds and free during the preview, or a [`professional`](https://heygen-1fa696a7.mintlify.site/docs/voices/professional-voice-clone) voice trained from 1–10 recordings (20+ minutes) on one purchased [voice clone slot](https://platform.heygen.com/usage). Both modes are in beta and speak through [Text to Speech](https://heygen-1fa696a7.mintlify.site/docs/voices/heygen-voice-speech.md), completed or streamed. [HeyGen Voice](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-voice.md#choose-a-mode) compares them in full.

## HeyGen Decision

[HeyGen Decision 1](https://heygen-1fa696a7.mintlify.site/docs/models/heygen-decision.md) answers named yes/no, choice, and score questions about [text](https://heygen-1fa696a7.mintlify.site/docs/models/decision/text.md), [images](https://heygen-1fa696a7.mintlify.site/docs/models/decision/image.md), [video](https://heygen-1fa696a7.mintlify.site/docs/models/decision/video.md), and [audio](https://heygen-1fa696a7.mintlify.site/docs/models/decision/audio.md) in one synchronous call to `POST /v3/models/decisions`, with a probability for every answer.


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