HeyGen Avatar IV

Talking avatar from a single photo: the model reads vocal tone and rhythm, then builds lifelike expressions and hand gestures. Sync from text or an existing voiceover.

Cost

3 tokens/s

VideoProvider: HeyGen

Run generation

IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"heygen-photo-avatar","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","resolution":"720p","avatarPhoto":"asset://asset_..."}}'

Input fields

* required

Field	Type	Default	Allowed
prompt`prompt` Exact speech script for the generated performance.	string	—	up to 5000 chars
aspectRatio`aspectRatio`	string	9:16	16:9, 9:16
resolution`resolution`	string	720p	1080p, 720p
Avatar photo*`avatarPhoto` Asset input for the avatarPhoto slot.	string	—	image · asset, https, data
Speech audio`speechAudio` Asset input for the speechAudio slot.	string	—	voiceover · asset, https, data

promptprompt

Exact speech script for the generated performance.

Type: string
Default: —
Allowed: up to 5000 chars

aspectRatioaspectRatio

Type: string
Default: 9:16
Allowed: 16:9, 9:16

resolutionresolution

Type: string
Default: 720p
Allowed: 1080p, 720p

Avatar photo*avatarPhoto

Asset input for the avatarPhoto slot.

Type: string
Default: —
Allowed: image · asset, https, data

Speech audiospeechAudio

Asset input for the speechAudio slot.

Type: string
Default: —
Allowed: voiceover · asset, https, data

Cost

3 tokens/s

Capabilities

Modesimage_to_video

Asset slotsavatarPhoto:image*speechAudio:voiceover

Run HeyGen Avatar IV

Get an API key and the same request shape will work across every model in the catalog.

Get API key Open in playground

Where to use this model

AI video generator Image to video