Logo
Image
Video
Voice
Apps
Motion Control
Avatar StudioNew
Marketing StudioNew
More
New
Other
Pricing

Turn your idea into video

Ready to create some AI magic? Describe your scene, pick your settings, and watch as AI brings your vision to life in stunning video.

Write a detailed prompt describing your video scene
Optionally upload reference images or videos
Hit generate and create cinematic videos in minutes
Start creating on the left
Alibaba

WAN 3.0 — Alibaba's latest unified video AI with native audio

WAN 3.0 is Alibaba's newest video generation model on Zyka. Unified text-to-video and image-to-video with native audio, up to 30 seconds, and 480p–1080p output.

  • Unified T2V and I2V
  • Native audio generation
  • Up to 30 second clips
  • 480p, 720p, and 1080p
  • Adaptive aspect ratio

How WAN 3.0 Works

01

Choose your input

Start from a text prompt alone (T2V), or upload a start frame — optionally with an end frame for interpolation (I2V).

02

Configure output

Pick resolution (480p–1080p), duration (2–30s), aspect ratio, and whether to include generated audio.

03

Generate the clip

WAN 3.0 produces smoother motion and stronger scene coherence than earlier WAN generations.

About WAN 3.0

WAN 3.0 is Alibaba's latest-generation video model on Zyka, succeeding WAN 2.7 with improved motion smoothness, scene fidelity, and visual coherence.

Unlike WAN 2.6's separate T2V and I2V models, WAN 3.0 is a single unified model — one form handles text-only, image animation, and start/end frame interpolation.

Native audio generation is built in: enable sound generation to produce synchronized audio alongside your video without uploading a separate audio file.

Frequently Asked Questions

How is WAN 3.0 different from WAN 2.7?

WAN 3.0 supports longer clips (up to 30s vs 15s), 480p resolution, adaptive aspect ratio, and native audio generation. It uses fal's alibaba/wan-3.0 endpoints.

Does WAN 3.0 support image-to-video?

Yes. Upload a start frame to animate it, or add both start and end frames for interpolation — all in the same model.

Can I upload my own audio?

WAN 3.0 generates audio natively via a toggle. Custom audio upload is not supported on this model — use WAN 2.6 or 2.7 for uploaded audio workflows.

What resolutions are available?

480p, 720p, and 1080p. Pricing scales with resolution per second of output.

How much does WAN 3.0 cost?

Billing is per second of video at fal rates plus 20%: 6 credits/s at 480p ($0.06/s), 12 credits/s at 720p ($0.12/s), and 24 credits/s at 1080p ($0.24/s). T2V, I2V, and reference-to-video use the same rate. Example: a 5s clip at 720p costs 60 credits.