Generate video from text with Veo and Kling.
Describe a scene and get a video. Yout.chat runs top text-to-video models — Veo 3 and Kling 2 — under your credits, so you can prototype clips, ads and B-roll from a prompt without a separate video subscription.
Features
Veo 3 (fast) and Kling 2 Master for high-quality text-to-video.
Describe the shot — subject, motion, style — and generate a short clip.
Video spends the same credits as chat and image; no extra plan.
Jobs run server-side — start one and keep working while it renders.
How to use AI Video Generator
- Open the chat and sign inVideo generation needs an account with credits.
- Switch to Video modeClick the Video chip above the composer.
- Describe your clipWrite a prompt with subject, action and style.
- Generate and playSend to start the render; the clip appears inline when ready.
API example
Use your Yout.chat key with the OpenAI-compatible API. Full API docs →
curl https://api.yout.chat/api/media/video/ \
-H "Authorization: Bearer $YOUT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fal-ai-veo3-fast",
"prompt": "a drone shot flying over a misty pine forest at sunrise"
}' Frequently asked questions
Which video models are available?
Veo 3 (fast) and Kling 2 Master, with more added over time.
How long does a video take?
Typically under a couple of minutes; jobs run in the background so you can keep using the chat.
How much does a video cost?
Video is the most compute-heavy modality — roughly 600K–1.5M credits per clip depending on the model. The cost is shown before you generate.
Do I need a separate plan?
No — video uses the same credits as chat, image and voice.
Related tools
Generate a video
One subscription, every model and modality. Start free.