> ## 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: the Avatar V, Avatar IV, and Avatar III rendering engines, and the HeyGen Voice model for voice cloning and speech.
Highest fidelity. Opt-in per look.
Default engine. Broadest coverage.
Photo-to-video pipeline. 4K.
Voice clones and speech.
The v3 API exposes two kinds of models. **Avatar rendering engines** turn a look and a script into video, selected per request through the `engine` field on [`POST /v3/videos`](/reference/create-video). The **[HeyGen Voice](/docs/models/heygen-voice)** model clones a speaker and synthesizes speech, on its own or as the narration of an avatar video.
## Avatar rendering engines
New integrations should default to [Avatar IV](/avatar-iv) for broad coverage, opt into [Avatar V](/avatar-v) for the highest-fidelity motion and lip-sync, and use [Avatar III](/avatar-iii) for its 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": "avatar_iv" }
}
```
Before requesting an engine, confirm the look supports it: `supported_api_engines` on [`GET /v3/avatars/looks/{look_id}`](/reference/get-avatar-look) lists which of `avatar_iii`, `avatar_iv`, and `avatar_v` the look accepts. Requesting an engine that isn't listed returns `400`.
| | [Avatar V](/avatar-v) | [Avatar IV](/avatar-iv) | [Avatar III](/avatar-iii) |
| -------------------------- | --------------------- | ----------------------- | --------------------------- |
| `engine.type` | `avatar_v` | `avatar_iv` | `avatar_iii` |
| API version | v3 | v3 | v3 |
| Default engine | ✗ (explicit opt-in) | ✓ | ✗ (explicit opt-in) |
| Available to new users | ✓ | ✓ | ✓ |
| Digital Twin | ✓ | ✓ | ✓ |
| Photo Avatar | ✗ | ✓ | ✓ (dedicated pipeline) |
| Studio Avatar | ✗ | ✓ | ✓ (renders as Digital Twin) |
| Arbitrary image input | ✗ | ✓ | ✗ |
| `motion_prompt` | ✓ | ✓ | ✗ |
| `expressiveness` | ✗ | ✓ | ✗ |
| Cross-reference animation | ✓ | ✗ | ✗ |
| 4K output | ✗ | ✗ | ✓ (except Photo Avatar) |
| Eligibility check required | ✓ | ✗ | ✗ |
A separate, older Avatar III engine remains available to existing customers through the **legacy v1/v2 endpoints**. It uses a different pipeline and is **not** the same as the Avatar III (`avatar_iii`) engine documented here. See [Avatar III](/avatar-iii#legacy-avatar-iii-v1v2) for the distinction.
## HeyGen Voice
[HeyGen Voice](/docs/models/heygen-voice) is HeyGen's in-house voice model. Clone a speaker at one of two tiers; the tier decides which endpoints you use afterward.
| | [Instant Clone](/docs/voices/instant-voice-clone) | [Professional Clone](/docs/voices/professional-voice-clone) |
| ------------ | ------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------- |
| Source audio | One recording | 1–10 recordings, 20+ minutes in total |
| Ready in | Minutes | Asynchronous training; poll until `ACTIVE` |
| Runs on | Starfish engine | Dedicated HeyGen Voice adapter per speaker |
| Create with | [`POST /v3/voices/clone`](/reference/clone-a-voice) | `POST /v3/models/audio/voices` |
| Speech | [Third Party Speech](/docs/voices/speech) and [`POST /v3/videos`](/reference/create-video) | [HeyGen Voice Speech](/docs/voices/heygen-voice-speech), completed or streamed |
| Availability | All API plans | Beta, private preview. Paid: one purchased [voice clone slot](https://app.heygen.com/developers/usage) per voice |
Stock and [designed voices](/docs/voices/design-voices) from the [voice catalog](/docs/voices/overview) synthesize through the same Starfish path as instant clones.