Text to video: generate a clip from a prompt

tendre.AI turns a text prompt into a short video clip with real motion and synchronized sound, powered by LTX 2.5. This is the same screen used for image to video, just without a starting image.

1. Open Create a video

In the sidebar, open the Video group and select Create a video. This single screen handles both text to video and image to video: skip the starting image step and you get text to video.

2. Pick a render engine

Choose Local to render for free on your own GPU (unlimited), or Cloud to render on tendre.AI's servers using credits, no install needed and gated behind an activated license. In Cloud, also pick a mode: Fast for a quick, cheap draft, or Quality for a finished clip with voice. Ultra gives the finest render, at a fixed price per clip. See Fast, Quality or Ultra.

3. Describe the scene

Write a prompt describing the subject, the action and the setting in the Motion field, for example "a woman walks through a neon-lit street, camera slowly follows." Use the camera move dropdown right next to it to add a cinematic move without typing it yourself.

4. Set sound, length and format

Toggle Sound on for audio generated alongside the motion, drag the length slider (4 to 20 seconds, 10 seconds max on Turbo), and pick a format (Square, Portrait, Landscape) and resolution.

5. Generate

Press Generate. Local renders use your GPU; Cloud renders show the estimated credit cost first, with a progress bar tracking queueing then rendering.

See Image to video to animate a still on the same screen, and Camera movements for the full list of moves.