SkytellsVideo modelVideo Agent
Video Agent is a video model by Skytells. It supports text to video, video agent, character replacement, object replacement, identity preservation, avatar, motion.
Model availability and access depend on your workspace and plan.
About the model
Video Agent, explained.
Video Agent is a video model by Skytells. It supports text to video, video agent, character replacement, object replacement, identity preservation, avatar, motion.
Supported capabilities
- Text to video
- Video agent
- Character replacement
- Object replacement
- Identity preservation
- Avatar
- Motion
What you get back. Your generated video appears directly in your Relam chat.
Working with Video Agent
Shape the result.
Prompt
Required inputText prompt describing the video you want to create. The Video Agent handles avatar selection, scripting, scenes, and editing.
Style Id
Optional inputVisual style template ID from Skytells' curated styles. Controls scene composition, pacing, and aesthetics.
Voice Id
Optional inputVoice ID for narration. If not provided, the Video Agent selects a voice automatically.
Avatar Id
Optional inputAvatar ID to use. If not provided, the Video Agent selects an appropriate avatar.
Orientation
Optional inputVideo orientation. Must be "landscape" or "portrait". Leave empty to let the Video Agent decide.
Duration Sec
Questions & answers
More about Video Agent.
Video Agent is a video model by Skytells. It supports text to video, video agent, character replacement, object replacement, identity preservation, avatar, motion.
Skytells is the vendor behind Video Agent, a video model available in the Relam catalogue.
Text prompt describing the video you want to create. The Video Agent handles avatar selection, scripting, scenes, and editing. This input is required.
Visual style template ID from Skytells' curated styles. Controls scene composition, pacing, and aesthetics.
Voice ID for narration. If not provided, the Video Agent selects a voice automatically.
Avatar ID to use. If not provided, the Video Agent selects an appropriate avatar.
Video orientation. Must be "landscape" or "portrait". Leave empty to let the Video Agent decide.
Approximate target duration of the video in seconds. Minimum is 5.
Open your Relam workspace and look for Video Agent in the video model selector. Its required inputs are prompt. Available models, controls and access depend on your workspace and plan.