Want a moving picture? Ask for one. In an agentic chat, describing the clip you want is enough — Catalyst renders a short video and drops it straight into the reply, with an inline player: play, pause, and full-screen, right there in the conversation.
There are two ways to get a clip:
Write what you want to see happen — the subject, the motion, and how the camera moves:
Make a video of a paper boat drifting down a rain-soaked street, camera following slowly from behind.
The assistant tells you it’s starting the render and roughly how long it will take, then the finished clip appears inline in its reply. Text-to-video runs on LTX-Video, the fast default (more on the models below).
The image-to-video flow pairs naturally with image generation: make the still first, then set it in motion.
Get the still into the chat — attach an image to your message, or ask Catalyst to generate one (“generate an image of a lighthouse on a cliff at dusk”).
Ask for motion, describing what should move:
Animate this — waves crashing below, the lighthouse beam sweeping across the frame.
Catalyst animates it and returns the clip inline, right below your still.
This two-step pattern — generate a still, then animate it — is also how you make a moving version of something that doesn’t exist yet. Want an animated logo of a fox? Ask for the image first, get it looking right, then say “animate it.” Catalyst handles both steps for you in the same conversation.
This is what sets Catalyst’s video apart. The default model, LTX-Video, generates a synchronized audio track — including spoken dialogue. Put the actual lines in your prompt, in quotes, and the characters speak them, roughly lip-synced.
Close-up of a barista sliding a coffee across the counter. She looks up, smiles, and says, “Careful — it’s hot.”
The catch is timing: spoken audio runs at roughly two to three words per second, so the dialogue has to fit inside the clip’s length. Keep it short.
If a line is too long to land inside the clip, trim it rather than let it overflow. Audio comes with both LTX-Video (the dialogue specialist) and MiniMax H3 (strongest at score, ambience, and sound effects) — only the WAN model below is silent. For anything with talking or narration, stay on the default.
You don’t normally pick a model — the assistant chooses the right default for what you asked. Workspace admins curate which video models are available under Admin → Video Models. Three models cover the range:
LTX-Video — fast, with audio (default)
The default for both text-to-video and image-to-video. Fast, and the best model for spoken dialogue — characters voice your lines, roughly lip-synced. Use it for almost everything, and always when someone talks.
MiniMax H3 — cinematic, multi-shot, with audio
The film-maker. A realistic, cinematic look, and the only model that can cut between shots inside one clip — describe a shot-by-shot sequence and it edits them together, with a scored soundtrack (music, ambience, effects). Slower (a few minutes). Ask for a “cinematic” or “trailer-style” clip, or say “use MiniMax.”
WAN 2.2 — image-to-video, silent
An image-to-video only alternative. Noticeably slower (around three minutes) and silent — no audio. Reach for it by name — “use WAN” — when you want its particular look for animating a still and don’t need sound.
Video is far heavier than images, and Catalyst renders it synchronously while you wait.
Video prompts reward different habits than image prompts:
A generated clip renders as a native video player inline in the reply — with standard controls — and it travels with the conversation. Expand it full-screen from the lightbox, and anyone viewing a shared chat can play it too.
Under the hood, plain language is all you need: a video-author
skill loads automatically and teaches the assistant how to pick the
model, budget dialogue to the clip length, and phrase prompts for motion — so you can just
ask for the clip you want.
