Golden hour drone
“Aerial drone shot rising over a coastal cliff at golden hour, waves breaking below, warm rim light, slow upward reveal of the horizon.”
Write what should happen on screen in a sentence or two. EveryGen AI expands it into a full shot, renders the clip with sound and keeps every version in the chat.
EveryGen AI text to video turns a written idea into a video clip. You describe the scene; the video agent adds subject, camera, light and pacing, chooses the model and renders the clip with sound.
Write in any language and keep it short. Clips run 4 to 30 seconds depending on the model, with aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, and you refine the result by replying in the same chat.
| Input | A written prompt in any language. Images, clips or audio can be added as references. |
|---|---|
| Models | MiniMax H3 and Seedance 2.5 |
| Clip length | MiniMax H3: 5–15 seconds; Seedance 2.5: 4–30 seconds |
| Resolution | MiniMax H3: 768P / 2K; Seedance 2.5: 480p / 720p |
| Aspect ratios | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, or picked automatically |
| Sound | Generated together with the picture on every model |
| Cost | MiniMax H3 at 2K: 100 credits per 5 seconds; Seedance 2.5 at 720p: 400 credits per 5 seconds |
| Output | MP4 video with audio, saved to the chat and your library |
One or two sentences is enough, for example “a paper dragon unfolds from a pop-up book”. Add style, camera or mood if you have them in mind.
EveryGen AI expands your words into a detailed prompt and renders with the model, length and aspect ratio set in the composer.
The clip renders with sound in a few minutes. Reply with changes such as “make it 9:16” or “slower camera”, and every take is kept.
Load one into the composer, send it as is or edit it first.
“Aerial drone shot rising over a coastal cliff at golden hour, waves breaking below, warm rim light, slow upward reveal of the horizon.”
“Slow tracking shot down a rainy neon-lit street at night, reflections rippling in the puddles, shallow depth of field, anamorphic flares.”
“Extreme macro shot of espresso pouring into a glass cup, crema swirling, soft window light from the left, steam curling upward, locked-off camera.”
“Time-lapse of clouds racing over red desert rock formations, shadows sweeping across the sand, deep blue sky, static wide shot.”
“Vertical 9:16 shot walking through a narrow Kyoto alley at dusk, lanterns switching on one by one, handheld energy, shallow focus.”
“Vertical 9:16 close-up of cheese pulling from a freshly cut slice of pizza, steam rising, warm restaurant lighting, slow motion.”
Name the subject and the action: who or what is on screen, and what happens.
Give one camera move, such as a push-in, an orbit or a handheld follow.
Set light and mood: golden hour, neon night, soft window light.
Say the format when it matters: 9:16 for TikTok, Reels and Shorts, 16:9 for YouTube.
Keep one shot per prompt, then ask for the next shot in the same chat.
You type a prompt, the video agent turns it into a detailed shot description, and the selected model renders it as a clip with sound. You then refine it by replying in the chat.
No. A sentence is enough. EveryGen AI adds camera, light and pacing for you, and you can still write a detailed prompt if you prefer.
Yes. EveryGen AI accepts prompts in any language.
Yes. Choose 9:16 in the composer, or ask for a vertical version in the chat. Supported ratios are 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
It depends on the model: MiniMax H3: 5–15 seconds; Seedance 2.5: 4–30 seconds.
Yes. Paid plans include a commercial license for the videos you make. Make sure your prompts do not copy protected characters, brands or real people without permission.
Type a sentence and get a clip with sound in a few minutes.