HeyGenAvatarVideoNode - ComfyUI Built-in Node Documentation

Generate a talking-presenter video from a HeyGen avatar.

Generate a talking-presenter video from a HeyGen avatar. This node creates a video of an AI avatar speaking your provided text or lip-syncing to your own audio, using HeyGen’s rendering engines.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
engine	Rendering engine; each choice lists only the avatars that support it. “auto” offers every avatar and picks its best engine (Avatar IV preferred). Avatar V is highest fidelity, Avatar III is the most affordable.	DYNAMIC_COMBO	Yes	"auto" "avatar_iv" "avatar_iii" "avatar_v"
custom_avatar_id	Optional HeyGen avatar look ID. When set, overrides the avatar selected above. Any of HeyGen’s 3000+ public looks (or your private avatars) can be used. Default: "".	STRING	No
speech	Drive the avatar with a text script (HeyGen text-to-speech) or your own audio. Display name: “speech source”.	DYNAMIC_COMBO	Yes	"script" "audio"
resolution	Output video resolution. Default: "1080p".	COMBO	No	"720p" "1080p"
aspect_ratio	Output aspect ratio. “auto” follows the avatar’s source footage. Default: "auto".	COMBO	No	"auto" "16:9" "9:16" "1:1" "4:5" "5:4"
background_color	Optional solid background color as a hex code (e.g. "#00ff00"). Leave empty for the avatar’s own background. If provided, the value must start with #. Default: "".	STRING	No
seed	Not sent to HeyGen; change it to force a re-run. Default: 42.	INT	No	Min: 0 Max: 2147483647

auto Inputs

When engine is "auto", the following sub-parameter is available:

Parameter	Description	Data Type	Required	Range
avatar	Avatar look to present the video (curated from HeyGen’s public library). The best engine the look supports is chosen automatically.	COMBO	Yes	Multiple options available

avatar_iv Inputs

When engine is "avatar_iv", the following sub-parameter is available:

Parameter	Description	Data Type	Required	Range
avatar	Avatar looks that support the Avatar IV engine.	COMBO	Yes	Multiple options available

avatar_iii Inputs

When engine is "avatar_iii", the following sub-parameter is available:

Parameter	Description	Data Type	Required	Range
avatar	Avatar looks that support the Avatar III engine.	COMBO	Yes	Multiple options available

avatar_v Inputs

When engine is "avatar_v", the following sub-parameter is available:

Parameter	Description	Data Type	Required	Range
avatar	Avatar looks that support the Avatar V engine.	COMBO	Yes	Multiple options available

script Inputs

When speech is "script", the following sub-parameters are available:

Parameter	Description	Data Type	Required	Range
text	Text for the avatar to speak (up to 5000 characters). The generated speech must be at least 1 second long. Default: "".	STRING	Yes	Min: 1 character Max: 5000 characters
voice	Voice for the script. The default option uses the voice HeyGen assigned to the avatar. Ignored if custom_voice_id is set.	COMBO	Yes	"(avatar's default voice)" Multiple general voice options available
custom_voice_id	Optional HeyGen voice ID. When set, overrides the voice selected above. Any voice from HeyGen’s library (2000+) can be used. Default: "".	STRING	No
voice_speed	Speech speed multiplier. Default: 1.0.	FLOAT	No	Min: 0.5 Max: 1.5 Step: 0.05

audio Inputs

When speech is "audio", the following sub-parameter is available:

Parameter	Description	Data Type	Required	Range
audio	Audio for the avatar to lip-sync, up to 10 minutes.	AUDIO	Yes

Note: engine and speech are selectors that reveal different sub-parameters depending on the chosen value. The speech selector has two mutually exclusive modes: in "script" mode, text is required; if custom_voice_id is provided, it overrides voice. In "audio" mode, the avatar lip-syncs to the provided audio clip. background_color must be a hex color code starting with # when provided. When custom_avatar_id is set, it overrides the avatar selection, and the selected engine must be supported by that avatar look; otherwise an error is raised unless engine is "auto".

Outputs

Output Name	Description	Data Type
VIDEO	The generated avatar presenter video.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): 86dc799d3a8cf2666449b0d422853b12feffb81ce002f84594f9b925d58b522a