Seedance 2.0 Fast Text to Video
Published April 1, 2026
About
ByteDance's most advanced text-to-video model in its fast tier delivering lower latency and cost without compromising on cinematic output, native audio, multi-shot editing, and director-level camera control for professional-grade video creation.
Documentation
Seedance 2.0 Fast Text to Video
ByteDance's fast-tier text-to-video model — delivers lower latency and ~20% cost savings compared to the standard version, without compromising on cinematic output, native audio, and camera control.
- Need higher resolution (1080p)? Try Seedance 2.0 Text to Video.
- Need image-driven generation? Try Seedance 2.0 Fast Image to Video.
- Need reference-guided generation? Try Seedance 2.0 Fast Reference to Video.
Highlights
Lower latency — Optimized for speed, ideal for iterative workflows and rapid prototyping.
Native audio generation — Automatically creates synchronized sound effects, ambient audio, and lip-synced speech.
Flexible duration — Generate 4 to 15 second clips. Use -1 for model-intelligent duration selection.
Up to 720p — Supports 480p and 720p output (1080p not available in fast tier).
Pricing
| Resolution | Price per second |
|---|---|
| 480p | $0.08 |
| 720p | $0.16 |
Default: 5 seconds at 720p = $0.80. Audio generation included at no extra cost.
Technical Specs
| Spec | Value |
|---|---|
| Input | Text prompt |
| Output | MP4 video with optional audio |
| Resolution | 480p / 720p |
| Aspect ratios | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 |
| Duration | 4–15 seconds |
| Execution | Async (submit → poll for result) |
| Typical latency | 1–5 minutes |
Related
- Seedance 2.0 Text to Video — Standard version with 1080p support
- Seedance 2.0 Fast Image to Video — Fast image-driven generation
- Seedance 2.0 Fast Reference to Video — Fast multi-reference generation
Try Seedance 2.0 Fast Text to Video
Test this model in the Sandbase Playground with your own prompts.
Open in Playground