ByteDance / Volcano Engine
Seedance 2.0
Seedance 2.0 adopts a unified multimodal audio-video joint generation architecture. The official page says it supports text, image, audio and video inputs, offers content reference and editing capabilities, and provides motion stability, director-level control, performance, lighting, shadow and camera movement controls. It is tracked as ByteDance Seed's current video-generation model separate from China-first Jimeng AI.
Quick answers
At a glance
- Overview
- ByteDance Seed's multimodal audio-video generation model for text, image, audio and video conditioned creation.
- Best fit
- Creators and developers comparing Chinese video models with multimodal input, audio-video generation and API access.
- Trust
- 2/2 sources verified, recently checked · 2026-05-17
- Coverage
- 100/100
Editorial verdict
Best for
Creators and developers comparing Chinese video models with multimodal input, audio-video generation and API access.
Avoid if
Avoid using it for committed client delivery until model access, output rights, billing and generation limits are confirmed.
Why it matters
Seedance 2.0 is ByteDance Seed's named video model and provides a direct way to track video capability instead of only through Jimeng or generic Doubao/Ark.
Pricing
API and Try Now access are linked from the official page; pricing should be checked in BytePlus or Volcano Engine
Payment
BytePlus billing, Volcano Engine billing
Commercial use
Commercial use should follow the current product, API, model license and billing terms.
Privacy
Review prompt, file, media upload, retention and training-use terms before sensitive workloads.
Use-case fit
Multimodal video generation
StrongUse it when text, image, audio and video references all matter for generated video.
Cinematic creative control
StrongThe official page highlights control over performance, lighting, shadows and camera movement.
Global user checklist
Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.
Pros
- - Official English page documents text, image, audio and video inputs
- - Targets audio-video joint generation and editing rather than silent video only
- - Includes Try Now and API entry points
Cons
- - Production access, quotas and API regions need account verification
- - Benchmark claims are based on ByteDance internal SeedVideoBench-2.0
Decision paths
kling-ai
hailuo-ai
qwen-wan-video
hunyuan-open-models
Sources
official · en · verified 2026-05-17
Documents Seedance 2.0 multimodal audio-video generation, controls, Try Now and API links.
official · en · verified 2026-05-17
Lists Seedance 2.0 in the GenMedia portfolio.