Seedance 2.0 Text To Video

Seedance 2.0 text-to-video generation with controllable duration, aspect ratio, resolution, and optional synchronized audio.

Model Overview

Seedance 2.0 Text To Video generates short video clips from text prompts. It supports 480p and 720p output, 4-15 second duration controls, flexible aspect ratios, and optional generated audio.

Best At

• Text-to-video generation with controlled framing and duration.
• Polished short clips from descriptive prompts.
• Iterating scene, camera, and motion direction without reference media.

Limitations / Not Good At

• Auto duration can make cost harder to estimate before generation.
• Highly specific choreography may need multiple prompt revisions.
• Longer clips are more sensitive to prompt ambiguity and scene drift.

Ideal Use Cases

• Generating finished short videos from text briefs.
• Creating campaign, social, and storyboard motion assets.
• Exploring visual styles before moving into reference-driven workflows.

Input & Output Format

• Input: required prompt; optional aspect_ratio, duration, resolution, generate_audio, and seed.
• Output: generated video URI returned on response.

Performance Notes

• Pricing scales with generated video size and duration.
• Use explicit duration instead of auto when predictable cost is important.