Text to Video

Most creators have the idea for the clip long before they have the footage. Text to Video closes that gap: you type what happens — who is in frame, where they are, what the camera does, what they say — and a short clip comes back with sound. It is built for the formats you actually post: 9:16 for Reels, Shorts and TikTok, 16:9 for YouTube b-roll and intros, 1:1 for feed posts. Clips run four to fifteen seconds, which is the length of a hook, a transition, a product reveal or a piece of b-roll under a voiceover. No stock library, no shoot day, no waiting on a friend with a camera.

The controls stay simple. The tier sets the engine: Draft is the cheapest way to test motion and timing, Standard is the everyday tier with sound and spoken lines, Pro is for the hero clip at up to 1080p. Resolution and length set the price per second, and the button always shows the total before you commit. Dialogue works by putting the line in quotes inside the prompt; the clip gets a voice for it. When you need the same character, product or style across several clips, attach up to nine reference images from your creations — the engine keeps them consistent from shot to shot. If the first frame is a photo of a real person, pick People: Standard and Pro can't animate real faces.

A good workflow is to write one line, render it on Draft, and look at the motion before spending more. Then switch to Standard for the version you post and Pro only for the one clip that carries the whole video. Every render lands in your creations rail with a poster frame; download it, make a variation with the same settings, or reframe a still from your rail and feed it in as a first frame with Photo to Video. Clips that get blocked by moderation or fail on the provider's side are refunded on Standard and Pro.