Long scene
30 seconds: a grandmother bakes a pie in a rustic kitchen, rolls out the dough, puts it in the oven, takes out a golden pie, and smiles at her grandson. Warm lighting, sound of a crackling stove.
Long videos up to 30 seconds with sound and 1080p
Wan 3.0 Prime from Alibaba generates long clips up to 30 seconds in a single pass, with audio and speech, in 1080p. Great for scenes that feel cramped in 5–10 seconds.
a person dances, runs, then flies and waves their hand
The person from the photo slowly turns to the camera and smiles. Wind in hair, sunset glow, smooth camera zoom-in.
Copy the prompt, insert your details — and get a video matching the sample.
30 seconds: a grandmother bakes a pie in a rustic kitchen, rolls out the dough, puts it in the oven, takes out a golden pie, and smiles at her grandson. Warm lighting, sound of a crackling stove.
Man in a podcast studio speaks into a microphone: «Today we will break down three mistakes every beginner makes». Soft lighting, bookshelves in the background.
A hot air balloon rises over a mountain valley at sunrise, camera slowly orbiting around it, wind sound audible.
| Plan | Price | Enough for |
|---|---|---|
| Free | free | — |
| Premium | 450 ★ · 1 month | up to 2 videos |
| Premium | 1 200 ★ · 3 months | up to 8 videos |
| Premium | 2 250 ★ · 6 months | up to 16 videos |
| Premium | 4 200 ★ · 12 months | up to 32 videos |
Did not find an answer? Message us, real people reply.
Contact support165 generations per 5 s video. Generations are the internal currency of AskMeAI: included with Premium and sold as one-time packs.
Wan 3.0 Prime is available with a Premium subscription and one-time generation packs. You can try photo effects and chat with free models for free.
Describe the action and camera in two or three phrases, and the sound in a separate one. Rely on the formula: character → action → camera → atmosphere → sound → format.
On the askmeai.ru website studio and in the @GPT5Telegbot Telegram bot — shared balance.
Video by Grok: bold stories, fast, and up to 1080p
Cinematic videos with sound from text prompts
Vivid emotions and facial expressions with sound
Cinema by Google: visuals, speech, and music in a single clip