Wan 3.0 AI Video Generator: Text & Image to Video with Sound
Create videos with Wan 3.0 on OCMaker AI: turn text or an image into a clip with native audio, 5 to 15 seconds long, up to 1080p.
Wan 3.0 is the newest model in Alibaba’s Wan video family. On OCMaker AI it turns a text prompt or a single image into a video with its own audio track — ambience, sound effects and voices are generated together with the picture. Pick 5, 10 or 15 seconds at 480p, 720p or 1080p.
Every clip on this page was generated with Wan 3.0 on OCMaker AI. The prompt we used is in each description.
0104
Describe a whole journey and Wan 3.0 follows it in a single continuous camera move. This 10-second clip came from text alone, with no image. Prompt: A small white paper boat drifts down a rain-filled street gutter, slips through a stone tunnel into a clear stream, floats past blooming hydrangeas and comes out into a sunlit harbor, where a young woman in a straw hat lifts it from the water and smiles.
0204
Upload an image and Wan 3.0 animates it from that exact first frame, so the people, outfits and setting stay as they are. The clip keeps the shape of your image. Prompt: The photo comes to life: he pulls the net tight, looks up toward the camera and breaks into a warm smile as seagulls glide past.
0304
Wan 3.0 adds a native audio track to every clip. Describe what should be heard, and put a short spoken line in quotes to give a character a voice. Prompt: Inside a tiny ramen shop at night, the chef slides a steaming bowl across the counter and says, “Extra spicy, just how you like it.”
0404
Choose 1080p when the detail matters: feathers, water droplets and fast wing motion stay crisp. Prompt: Macro shot: a hummingbird dips its beak into a red hibiscus covered in raindrops, wings blurring, then darts away.
What you get when you pick Wan 3.0 in the video generator above.
Start from a prompt alone, or upload an image to use as the first frame.
Ambience, sound effects and voices are generated with the video, at no extra cost.
Choose the clip length that fits your shot, from a quick moment to a longer scene.
Draft ideas at 480p, then render the one you like at 720p or 1080p.
Text-to-video clips come in 9:16 or 16:9; image-to-video keeps the shape of your image.
Wan 3.0 is available to members, from 10 credits for a 5-second 480p clip.
Three steps from an idea to a finished clip with sound.
Wan 3.0 is already selected in the generator above. Type a prompt for text to video, or add an image to animate it.
Say what happens, how the camera moves and what should be heard. Put any spoken line in quotes and keep it short enough for the clip.
Pick 5, 10 or 15 seconds and 480p, 720p or 1080p; the credit cost updates as you choose. Download the clip when it is ready.
Wan 3.0 is the newest video model in Alibaba’s Wan family. On OCMaker AI you can use it for text-to-video and image-to-video, and every clip comes with a native audio track.
Yes. Type a prompt without adding an image and Wan 3.0 generates the whole clip from text, in 9:16 or 16:9. Add an image when you want a specific character or scene to be the first frame.
Yes. Audio is always on and costs nothing extra. Describe ambience and sound effects in the prompt, and put a short line in quotes if a character should speak.
Each clip can be 5, 10 or 15 seconds long, at 480p, 720p or 1080p.
Wan 3.0 is available to members. At 480p a clip costs 10, 19 or 28 credits for 5, 10 or 15 seconds; at 720p 19, 37 or 55 credits; at 1080p 37, 73 or 110 credits.
Yes, in a separate mode. Reference to Video also runs on Wan 3.0 and combines several reference images, video clips and audio into one clip. Wan 3.0 also powers AI Story, which turns an idea into a multi-scene short.
Text or image to video with native sound, up to 15 seconds at 1080p.