Browse the current AI model catalog for video, audio, image, subtitle, background, and timeline generation workflows in Kepler Studio.
text / image to video
text / image to video
image + video to video
image + video to video
image + video to video
image + video to video
image + video to video
text / image to image
text / image to image
text / image to image
image to image
image to image
image to image
image to image
text to speech
text to speech
text to speech
text to speech / voice cloning
Fast prompt-to-sound generation for short timeline effects.
Prompt-to-sound generation with refinement controls for short effects.
Video-synced Foley and sound effects from a selected clip.
Frame interpolation (Video)
Speech-to-text model for timeline subtitle generation with word timing.
Creates in-between frames for smoother slow-motion video.
Quality interpolation for complex scenes with crossing objects, camera movement, and detailed motion.
Regenerates a selected moment inside an existing video shot.
Regenerates a selected moment inside an existing video shot.
Extends a shot forward or backward from rendered video context.
Structured music and soundtracks with precise duration control
Prompt-based video editing for selected timeline regions.
Fast, flexible music generation with duration and seed control
Higher-quality prompt-based video editing for selected timeline regions.
Complete vocal songs from style direction and structured lyrics
Clean spoken audio from clips or a selected timeline region
Prompt-based video generation with optional native audio and multi-shot storyboards.
Higher-quality prompt-based video generation with optional native audio and multi-shot storyboards.
Synchronize a rendered video region to a selected audio source.
High-quality lip synchronization for selected video regions.
Cost-efficient lip synchronization for selected video regions.