Video generation

Available now

Seedance 1.5 Pro

by ByteDance

ByteDance's audio‑visual video model.
Synced video and dialogue in one pass with multilingual lip‑sync and cinematic camera control.

Seedance 1.5 Pro

by ByteDance

Key features

Native audio-visual generation

Video and audio generate together in one pass, not stitched after. Dialogue, ambient sound, and on-screen action stay tightly synced.

Multilingual lip-sync with dialect support

Chinese, English, Japanese, Korean, Spanish, and Indonesian out of the box, with regional accents like Sichuanese and Cantonese.

Cinematic camera control

Dynamic cinematic camera control. Dolly, tracking, push-in, and orbital moves, with steadier narrative across the full clip.

Dual-branch DiT architecture

A dual-branch Diffusion Transformer with a cross-modal joint module aligns audio and video. Lip-sync, footsteps, and ambient cues hold.

Over 10× accelerated inference

End-to-end acceleration exceeds 10x via multi-stage distillation and infra tuning. Practical for iteration, not just final passes.

RLHF + SFT tuning

Post-trained with SFT on curated data and RLHF using multi-dimensional reward models. Prompt adherence and aesthetics skew production.

Technical specifications

480p / 720p / 1080p

Three resolution tiers

4–12s

Per-clip generation length

T2V + I2V

Both with native audio

Native

Joint audio-video generation

Use cases

Advertising creative with synced narration

Generate ad clips with dialogue, music, and on-screen action timed together in one pass, no separate audio mix required.

Short-form drama and dialogue

Dialogue-driven shorts where lip-sync, performance, and emotion need to read as a single take, especially across multilingual versions.

Localized ad rollouts

Generate the same ad with dialogue in multiple languages, lip-sync stays accurate per language, so localized variants don't look dubbed.

Image-to-video with audio

Start from a Seedream still, animate with Seedance 1.5 Pro and generate the matching audio in the same step.

Prompt examples

Ad with dialogue

Close-up of a barista handing over a coffee cup, smiling, says "enjoy your morning" in warm tone, ambient cafe sound, 8 seconds

Edit prompt

Cinematic shot

Slow dolly across a rainy neon-lit street at night, footsteps echoing, distant traffic, cinematic 1080p

Edit prompt

Image-to-video

Animate this still, the character looks up and speaks the line softly, matching lip-sync, soft room tone

Edit prompt

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

/ month

billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

/ month

billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

/ month

billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

/ month

billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits

Custom seat limits

All models

Workflows

Free

For playing around

forever free

Up to 20 credits

1 user only

Limited models

Workflows

Compare plan details

FAQs

What is Seedance 1.5 Pro?

Seedance 1.5 Pro is ByteDance's native audio-visual video generation model. It generates synchronized video and audio in one pass, including dialogue with multilingual lip-sync, optimized for ad creative and short-form drama.

How is Seedance 1.5 Pro different from Seedance 2.0?

1.5 Pro is the dedicated native audio-visual model with strong multilingual lip-sync and 10x-accelerated inference. 2.0 is the newer general-purpose flagship. Pick 1.5 Pro when dialogue and audio sync are the core of the brief.

Does Seedance 1.5 Pro generate audio?

Yes. Audio is generated jointly with the video, not added after. Dialogue, ambient sound, and timing are aligned at the millisecond level within the same forward pass.

What languages does the lip-sync support?

Seedance 1.5 Pro supports Chinese, English, Japanese, Korean, Spanish, and Indonesian, with native handling of regional accents including Sichuanese and Cantonese. Localized ad versions stay accurate per language rather than reading as dubbed.

How do I use Seedance 1.5 Pro on Morphic?

Open Copilot, describe the shot and the line of dialogue, and pick Seedance 1.5 Pro. For ad spots, dialogue-driven shorts, or any clip where audio and lip-sync are central, this is the right model over silent-video alternatives.

Can I pair Seedance 1.5 Pro with Seedream?

Yes. Generate a key still in Seedream or Seedream 4.5, then carry it into Seedance 1.5 Pro for image-to-video with synced audio, a clean end-to-end ByteDance pipeline on Morphic.

Seedance 1.5 Pro

Key features

Native audio-visual generation

Multilingual lip-sync with dialect support

Cinematic camera control

Dual-branch DiT architecture

Over 10× accelerated inference

RLHF + SFT tuning

Technical specifications

Use cases

Advertising creative with synced narration

Short-form drama and dialogue

Localized ad rollouts

Image-to-video with audio

Prompt examples

Ad with dialogue

Cinematic shot

Image-to-video

Simple pricing

FAQs

Other models