ByteDance's most advanced model with native audio, dance mode, character consistency, and multimodal input. Up to 2K resolution, 15 seconds.
Eight capabilities that set ByteDance's latest model apart
Dual-channel stereo audio generated alongside video in a single pass. Ambient sounds, dialogue, and music are all produced natively without post-processing.
Beat-matched choreography with lip-sync. Provide a music track and Seedance 2.0 generates characters dancing in perfect sync with the beat and lyrics.
Use the @tag system to maintain consistent faces and appearances across multiple shots. Create multi-scene narratives with the same characters throughout.
Combine up to 12 reference files including images, video clips, and audio tracks. Give the model rich context to produce exactly the output you envision.
Replace characters, add or remove elements from existing footage without regenerating the entire clip. Targeted edits that preserve the rest of your scene.
Seamlessly extend existing footage beyond its original duration. The model matches the style, motion, and context of the source material automatically.
Generate video at up to 2048x1080 at 24fps cinematic quality. A significant step up from 1080p, delivering sharper detail and professional-grade output.
Choose from 16:9, 9:16, 4:3, 3:4, 21:9, and 1:1. Cover every platform and use case from ultrawide cinema to vertical social media and square formats.
How ByteDance's latest compares to leading alternatives
| Feature | Seedance 2.0 | Seedance 1.5 | Kling 3.0 | Veo 3.1 |
|---|---|---|---|---|
| Max Resolution | ✓ 2K (2048x1080) | 1080p | 1080p | 4K |
| Max Duration | ✓ 15 seconds | 10 seconds | 10 seconds | 8 seconds |
| Native Audio | ✓ Stereo | No | No | ✓ Yes |
| Dance Mode | ✓ Yes | No | No | No |
| Character Consistency | ✓ @tag system | No | Limited | No |
| Multimodal Input | ✓ Up to 12 files | Image + text | Image + text | Image + text |
| Video Editing | ✓ Yes | No | No | No |
| Video Extension | ✓ Yes | No | ✓ Yes | No |
| Aspect Ratios | ✓ 6 options | Standard | 4 options | 3 options |
| Frame Rate | 24fps | 24fps | 24fps | 24fps |
Seedance 2.0 has restricted availability. Review the requirements below before requesting access.
Seedance 2.0 is available exclusively to Pro and Premium plan subscribers. Free and Starter plans do not include access.
You must register with a business email address. Consumer email providers such as Gmail, Yahoo, and Outlook are not accepted.
Seedance 2.0 is not available in the United States and Japan due to regulatory and licensing requirements from ByteDance.
Access must be reviewed and approved by the Aura AI team. You will receive a confirmation email once your request is processed.
Professional use cases powered by native audio and advanced video generation
Generate complete music videos with beat-matched choreography, lip-sync, and native audio. Dance Mode makes Seedance 2.0 the first AI model purpose-built for music content.
Create product showcase videos with consistent branding and character appearances across multiple shots. The @tag system ensures your model or spokesperson looks identical in every clip.
Produce vertical 9:16 content with native audio for TikTok, Instagram Reels, and YouTube Shorts. Generate scroll-stopping clips complete with sound in a single pass.
Generate 2K cinematic footage at 24fps for pre-visualization, concept work, and B-roll. Video editing features let you refine scenes without starting from scratch.
Everything you need to know about Seedance 2.0 on Aura AI
Native audio, dance mode, 2K resolution -- ByteDance's most powerful AI video model. Available for Pro and Premium business users.