Seedance 2.0 Text-to-Video

Generate video with native audio from a text prompt. Up to 4K, 4 to 15 seconds, seven aspect ratios, multi-shot scenes in one run.

By ByteDance

Pricing: $1.8662 per second

Overview

Seedance 2.0 Text-to-Video by ByteDance turns one prompt into a finished clip with sound. It cuts between shots inside a single run, holds real-world physics, and follows camera directions like push-in, orbit and handheld.

Key capabilities

• **From $0.16 per second** of generated video at 480p, $0.36 at 720p, $0.82 at 1080p and $1.87 at 4K. You pay for the seconds you get back.
• **Multi-region failover**, Runflow runs optimized inference across multiple regions. If one region has an outage, traffic routes to another automatically.
• **Native audio**: dialogue, foley and ambience are generated with the picture, so they stay in sync.
• **Multi-shot scenes**: describe a cut and the model delivers both shots in one video.
• **Seven aspect ratios**: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, or auto.
• **4 to 15 seconds**, or auto to let the model pick the length that fits the prompt.

Seedance family

| Variant | Input | Use it for |

|---|---|---|

| Seedance 2.0 Text-to-Video | text prompt | multi-shot clips up to 4K from a brief |

| Seedance 2.0 Reference-to-Video | text + up to 9 images | keeping a product or character consistent |

| Seedance 2.5 Text-to-Video | text prompt | single takes up to 30 seconds |

| Seedance 2.5 Reference-to-Video | text + up to 30 images | long takes with a locked cast and set |

Technical specifications

| Spec | Details |

|---|---|

| Resolutions | 480p, 720p, 1080p, 4K |

| Duration | 4 to 15 seconds, or auto |

| Audio | native, generated with the video |

| Frame rate | 24 fps |

| Output format | MP4 (H.264) |

| Latency | about 2 to 4 minutes for a 5 second 720p clip |

Examples

• Multi-shot clip: a keeper climbs to the lantern room, then a wide exterior of the beam over crashing waves, with thunder and rain audio

Frequently asked questions

What is Seedance 2.0 Text-to-Video?

Seedance 2.0 Text-to-Video is a ByteDance video model that generates a clip with synchronized audio from a text prompt. It supports 480p to 4K, lengths of 4 to 15 seconds, seven aspect ratios, and multiple shots inside one video.

How much does Seedance 2.0 Text-to-Video cost on Runflow?

You pay per second of generated video: $0.162 at 480p, $0.3641 at 720p, $0.8184 at 1080p and $1.8662 at 4K. A 5 second 720p clip costs about $1.82. Audio is included at no extra cost.

How long does a Seedance 2.0 Text-to-Video run take?

A 5 second 720p clip takes about 2 to 4 minutes. Higher resolutions and longer durations take proportionally longer. Submit the run and poll the run ID until it reports succeeded.

Can Seedance 2.0 Text-to-Video produce more than one shot?

Yes. Write the cut into the prompt, for example a close-up followed by a wide exterior shot, and Seedance 2.0 renders both shots in one continuous file.

Can I use Seedance 2.0 Text-to-Video output commercially?

Yes. Output from Seedance 2.0 Text-to-Video is licensed for commercial use. You keep the rights to the videos you generate.

Do I need to manage GPUs to run Seedance 2.0 Text-to-Video?

No. Runflow runs Seedance 2.0 Text-to-Video for you. You send one API call and get a video URL back. There is no GPU pool, no queue to operate and no AI team required.

How do I get started with Seedance 2.0 Text-to-Video?

Create a Runflow API key, then POST your prompt to /v1/models/bytedance/seedance-2.0/text-to-video/runs and poll the returned run ID until the video URL appears.

Related models

• Seedance 2.0 Reference-to-Video, Generate video with native audio from a text prompt plus up to 9 reference images. Up to 4K, 4 to 15 seconds, seven aspect ratios.
• Seedance 2.5 Text-to-Video, Generate a single coherent take of up to 30 seconds with native audio from a text prompt. Up to 1080p, seven aspect ratios.
• Happy Horse Text-to-Video, Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.

Discoverable surfaces

• Dispatch endpoint: POST https://api.runflow.io/v1/models/seedance-2.0/text-to-video/runs
• Per-model spec (markdown): https://app.runflow.io/models/seedance-2.0/text-to-video/llms.txt
• Docs page: https://docs.runflow.io/models/seedance-2.0/text-to-video
• Public OpenAPI spec: https://docs.runflow.io/api/openapi.public.json
• Agent skill (start here): https://www.runflow.io/.well-known/agent-skills/runflow/SKILL.md