Seedance 2.0 Text to Video

ByteD's flagship text-to-video model — generates cinematic video from text prompts with native audio, flexible duration, and director-level camera control.

• Need image-driven generation? Try Seedance 2.0 Image to Video.
• Need reference-guided generation? Try Seedance 2.0 Reference to Video.
• Need faster & cheaper? Try Seedance 2.0 Fast.

Highlights

Native audio generation — Automatically creates synchronized sound effects, ambient audio, and lip-synced speech. Toggle with generate_audio parameter.

Pure imagination — No input image required. Describe your scene and the model brings it to life with cinematic quality.

Flexible duration — Generate 4 to 15 second clips in a single request. Use -1 for model-intelligent duration selection.

Up to 1080p — Full HD output with support for 6 aspect ratios including cinematic 21:9.

Pricing

Resolution	Price per second
480p	$0.10
720p	$0.20
1080p	$0.50

Default: 5 seconds at 720p = $1.00. Audio generation included at no extra cost.

When to Use

✅ Good fit	❌ Consider alternatives
Creative concept visualization	Real-time video streaming
Social media content creation	Long-form video (>15s)
Marketing and ad clips	Pixel-perfect frame control
Storyboard-to-video workflows	Image-guided generation (use I2V)
Quick video prototyping	Multi-reference scenes (use Ref2V)

Technical Specs

Spec	Value
Input	Text prompt
Output	MP4 video with optional audio
Resolution	480p / 720p / 1080p
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	2–8 minutes

Related

• Seedance 2.0 Image to Video — Transform images into video
• Seedance 2.0 Reference to Video — Multi-reference guided generation
• Seedance 2.0 Fast Text to Video — ~20% cheaper, lower latency