Make Wan AI videos with sound from a prompt
Get a clip with its sound already in place from a single prompt. Wan 2.5 makes the audio together with the picture, in the same MP4. Your clip is ready to share, with no separate audio track to add.
Wan AI video generator on Pixelcut
Turn a prompt or one photo into a clip with sound from Alibaba's Wan AI. Pick 16:9, 9:16 or 1:1 and get an MP4 in about a minute and a half.
Model
Wan 2.5 on Pixelcut
Wan 2.5 by Alibaba comes preselected. Give it a prompt or one start photo and it returns a short clip with sound. Wan 2.2 is also here, and both run on Pixelcut Pro.
Wan 2.5 at a glance
- Input
- Text or photosOptional start photo
- Resolution
- 1280 × 1280
- Aspect ratio
- 1:1, 9:16, and 16:9Landscape, vertical or square
- Output
- MP4
- Clip length
- 5 to 10 s
- Audio
- No sound
Wan 2.2 at a glance
Explore Wan 2.2- Input
- Text or photosOptional start photo
- Resolution
- 1280 × 1280
- Aspect ratio
- 1:1, 9:16, and 16:9Landscape, vertical or square
- Output
- MP4
- Clip length
- 5 s
- Audio
- No sound
See clips from the Wan video generator
Pick a clip you like, keep its idea, and swap in your own subject, place or camera move.
Two ways to start
Try Wan text to video or image to video
Text to video works from words alone, for a scene you can picture but have no photo of. Image to video starts from one photo of yours, and the prompt only has to describe the motion. Either way, Wan 2.5 hands back a short MP4 with sound.
- Write a prompt, or upload one start photo
- Describe the action and where the camera sits
- Generate, then save the MP4
A brown pelican tucks its wings, plunges bill first into a turquoise cove and bobs up with its throat pouch full of water.
Bring a photo to life with Wan image to video
Turn a still you love into a moving clip. Wan 2.5 picks up from your photo as the first frame and carries the scene forward. Any common photo works, and Pixelcut sizes it for you.
Frame each Wan video in 16:9, 9:16 or 1:1
Each run makes one shape, picked before you generate. Go tall for Reels and Shorts, square for a feed post, or wide for YouTube. Want one idea in two shapes? Run the same prompt twice.
Lead each Wan 2.5 prompt with what matters most
Your clip keeps the heart of your idea when the prompt leads with it. Pixelcut sends the first 800 characters to Wan 2.5 and cuts the rest. Open with who is in the scene and what they do. Style notes can go at the end.
Put Alibaba Wan to work for your clips
Creators, online sellers and filmmakers use it for vertical posts, product clips and test shots before a shoot.
Reels and Shorts creators
Post vertical clips that hook viewers in the first seconds. Your Wan 2.5 clip arrives with its sound already in place, ready for Reels and Shorts.
Online sellers and brands
Show a product doing the one thing that sells it. You can generally put the clip in listings and ads when you own the photos and words you use.
Filmmakers testing big shots
See the expensive shot before you pay for the shoot or the effects. Compare the same idea in Pixelcut's AI video generator.
More models on Pixelcut
Switch models per generation instead of per subscription. Each card opens that model's page.
Cinematic motion, and your first video is free
- New
- Free with sign-up
- Image to video
- Up to 10 s
ByteDance's newest video model
- New
- Audio
- Image to video
- Up to 30 s
Text, image and reference video, up to 15 s
- New
- Audio
- Image to video
- Up to 15 s
Photoreal video with synchronized audio
- Audio
- Image to video
- Up to 8 s
Multi-shot scenes and elements
- New
- Audio
- Image to video
- Up to 15 s
How to create a Wan video on Pixelcut
- 1
Describe your Wan clip
Type what should happen in the clip in plain words, as you would tell a friend. To start from a picture instead, upload one photo and write how it should move.
- 2
Pick version and shape
Keep Wan 2.5 in the model picker or switch to Wan 2.2. Then pick 16:9, 9:16 or 1:1, whichever shape suits the place you plan to post the clip.
- 3
Generate and download it
Press generate and your clip is ready in about a minute and a half, as the model picker estimates. Download the MP4, or change one word in the prompt and run it again.
Plans for video generation
Video is billed in credits per second of footage. Pick the plan that matches how much you make.
Save 20% with a yearly plan
Free
$0
per month, billed yearlyYour first video free on MiniMax H3 Max
Image tools free to try
Pro
$10$8
per month, billed yearly600 AI Credits Monthly
Access all AI models
Unlimited Background Removal
Unlimited Upscale
3 Person Team
1,000 Batch Exports Monthly
Commercial license
Most Popular
Business
$30$24
per month, billed yearly3,600 AI Credits Monthly
Access all AI models
Unlimited Background Removal
Unlimited Upscale
10 Person Team
2,000 Batch Exports Monthly
Commercial license
Trusted by over 200,000 creators, brands and small businesses
Trusted by creatives at
Frequently Asked Questions
Wan AI is Alibaba's family of AI video models, built by its Tongyi lab, that turn text prompts and photos into short clips. Pixelcut runs two Wan versions, with Wan 2.5 preselected.
Pick Wan 2.5 for sound made with the picture. It is the later version and comes preselected. Wan 2.2 takes the same prompt or start photo and offers the same three shapes.
Yes, on Wan 2.5. Its clips come with sound made together with the picture, and both arrive in the same MP4, with nothing to line up in an editor afterwards.
Yes. Both Wan versions run on Pixelcut Pro, and the plans are in the pricing section on this page. With Pro, Wan 2.5 is ready in the prompt box at the top.
Generally, yes. You can put Wan AI clips in listings, ads, social posts and client work, as long as you hold the rights to your prompt inputs and photos and follow Pixelcut's policies.
Yes, through the Pixelcut MCP server, which works in Claude, ChatGPT, Codex and Cursor. Your agent can send Wan 2.5 a prompt alone or with one start photo, and each clip uses Pixelcut credits.
