Models - HeyGen Documentation

HeyGen Video

Prompt to video. Generates the whole frame.

Avatar 6

Newest avatar engine. Up to 2K.

Avatar V

Highest fidelity. Opt-in per look.

Avatar IV

Default engine. Broadest coverage.

Avatar III

Photo-to-video pipeline. 4K.

HeyGen Voice

Voice clones and speech.

The v3 API exposes three model families.

HeyGen Video

HeyGen Video generates video from a prompt, inventing the subject, the setting and the sound together in one call to POST /v3/models/videos.

HeyGen Avatar

Avatar rendering engines turn a look and a script into video, selected per request through the engine field on POST /v3/videos. New integrations should start with Avatar 6. Avatar V and Avatar IV (the default when engine is omitted) cover looks outside Avatar 6, and Avatar III runs a dedicated photo-to-video pipeline.

{
  "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} 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	Avatar V	Avatar IV	Avatar III
`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	✗	✓	✗
`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 is HeyGen’s in-house voice model. Clone a speaker on POST /v3/models/audio/voices as an instant voice from one recording, ready in seconds and free during the preview, or a professional voice trained from 1–10 recordings (20+ minutes) on one purchased voice clone slot. Both modes are in beta and speak through Text to Speech, completed or streamed. HeyGen Voice compares them in full.

HeyGen Video

Avatar 6

Avatar V

Avatar IV

Avatar III

HeyGen Voice

​HeyGen Video

​HeyGen Avatar

​HeyGen Voice

HeyGen Video

HeyGen Avatar

HeyGen Voice