HeyGen Avatar (Digital Twin)

HeyGen Avatar (Digital Twin) — generate a talking-avatar video from a script or an audio track. Both versions pick the avatar from HeyGen's stock catalog. A custom (cloned) voice ID works on Avatar IV only.

Try HeyGen Avatar (Digital Twin) in the playground

Last updated View as MarkdownAgent setup

HeyGen Avatar (Digital Twin)

Badge: New
Node type: video:heygen_avatar4_digital_twin
Category: video

Description

HeyGen Avatar (Digital Twin) generates a talking-avatar video from a script or an audio track: connect your script to the Prompt (v5 only) port or your audio to the Audio URL port, and the clip comes out of Generated Video, with Caption File (SRT, v5) as a second output. In the sidebar, Model offers v5 and v4. Both versions pick the avatar from HeyGen's stock catalog: choose one in Avatar (v5), or on v4 enter it in Avatar Name; left blank, that field uses the Avatar above it. Custom Avatar ID needs your own HeyGen key and is marked not supported. A custom cloned voice works on v4 only, where Custom Voice ID overrides Voice. The node costs about 16 credits per second, which is the rate for a 5-second clip; shorter clips can cost a bit more per second, and you're always charged for the real length.

Pricing

  • Cost: ~16 credits per second
  • Per-second rate: The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length.

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt (v5 only) TEXT · multiline
audio_url Audio URL AUDIO

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
model_version Model TEXT · options: v5, v4
avatar Avatar (v5) TEXT · options: Abigail Office Front, Abigail Office Side, Abigail Sofa Front, Abigail Sofa Side, Amelia Business Training Front 2, +495
avatar_id Custom Avatar ID (needs your own HeyGen key — not supported) TEXT
character Avatar Name (v4 — blank = use Avatar above) TEXT
voice Voice TEXT · options: Warm Pro Narrator, Chill Brian, Ivy, John Doe, Monika Sogam, +97
voice_id Custom Voice ID (v4 only — overrides Voice) TEXT
aspect_ratio Aspect Ratio TEXT · options: 16:9, 9:16, 1:1, 4:5, 5:4, +1
resolution Resolution TEXT · options: 360p, 480p, 540p, 720p, 1080p, +1
output_format Output Format (v5) TEXT · options: mp4, webm
fit Fit (v5) TEXT · options: contain, cover
remove_background Remove Background (v5) BOOLEAN
background_type Background Type (v5) TEXT · options: color, image
background_value Background Value (v5) TEXT
caption Caption SRT (v5) BOOLEAN

Outputs

ID Label Type
video Generated Video VIDEO
caption_file Caption File (SRT, v5) TEXT

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.