heygen/avatar-v

Official View on Replicate →

Create realistic talking avatar videos from text with HeyGen's Avatar V engine — the newest, highest-quality avatar engine with cross-reference-driven animation.

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`avatar_id` *	string	Avatar ID. Must be an avatar that supports Avatar V — check `supported_api_engines` on the look via the HeyGen API.	`—`	—
`input_text` *	string	Text that the avatar will speak. Must be less than 5000 characters.	`—`	—
`voice_id` *	string	Voice ID. Get available voice IDs from the HeyGen List All Voices API.	`—`	—
`aspect_ratio`	string	Output video aspect ratio.	`"16:9"`	16:9 9:16
`caption`	boolean	Whether to burn captions into the rendered video.	`false`	—
`resolution`	string	Output video resolution.	`"1080p"`	720p 1080p 4k
`title`	string	Title of the video.	`""`	—
`voice_speed`	number	Voice speed multiplier. Value ranges from 0.5 to 1.5.	`1`	min: 0.5, max: 1.5

avatar_id required string

Avatar ID. Must be an avatar that supports Avatar V — check `supported_api_engines` on the look via the HeyGen API.

input_text required string

Text that the avatar will speak. Must be less than 5000 characters.

voice_id required string

Voice ID. Get available voice IDs from the HeyGen List All Voices API.

aspect_ratio string

Output video aspect ratio.

Default: "16:9"

16:9 9:16

caption boolean

Whether to burn captions into the rendered video.

Default: false

resolution string

Output video resolution.

Default: "1080p"

720p 1080p 4k

title string

Title of the video.

Default: ""

voice_speed number

Voice speed multiplier. Value ranges from 0.5 to 1.5.

Default: 1 min: 0.5, max: 1.5

Version: 5b73419f1f34 Updated: 6/26/2026 130 runs