Seedance 1.5 Pro
Seedance 1.5 Pro is a joint audio-video generation model that delivers film-grade visuals, native multilingual audio, and emotionally coherent storytelling through precise instruction following.
Input
Prompt
Audio
Duration(s)
Resolution
Aspect Ratio
- auto
- 16:9
- 9:16
- 1:1
- 4:3
- 3:4
- 21:9
Return Last Frame
Camera Fixed
Result
View History| Model & Modality | Credits / Gen | Our Price (USD) | Official Price (USD) | DISCOUNT |
|---|---|---|---|---|
seedance 1.5 pro, i2v, t2v, 480p videoByteDance | 2 per second | $0.0089 | $0.012 | - 26% |
seedance 1.5 pro, i2v, t2v, 720p videoByteDance | 4 per second | $0.0179 | $0.026 | - 31% |
seedance 1.5 pro, i2v, t2v, 1080p videoByteDance | 8.75 per second | $0.0391 | $0.058 | - 33% |
seedance 1.5 pro, i2v, t2v, with audio-480p videoByteDance | 4 per second | $0.0179 | $0.024 | - 25% |
seedance 1.5 pro, i2v, t2v, with audio-720p videoByteDance | 8 per second | $0.0357 | $0.052 | - 31% |
seedance 1.5 pro, i2v, t2v, with audio-1080p videoByteDance | 17.5 per second | $0.0781 | $0.116 | - 33% |
Doubao Seedance 1.5 Pro API
Seedance 1.5 Pro, the latest audio and video generation model from ByteDance, delivers film-quality videos with synchronized audio and multilingual dialogue. It also supports cinematic camera movement control.
Prompt:
Soft light pours down, silk shimmering with a pearlescent sheen. She gently walks toward the camera, the skirt draping and flowing, outlining a form that is both soft and luxurious.
Everything you need to build
AI-powered applications
Our API provides comprehensive access to cutting-edge AI tools, enabling you to build sophisticated applications with ease.
Native Audio Generation
Video and audio are generated simultaneously, achieving perfect lip-sync and acoustic consistency without post-processing.
Audio-Visual Synchronization
Dual-Branch Diffusion Transformer architecture ensures natural alignment of lips, voice, and visuals.
Cinematic Visual Quality
Precise control of lighting, composition, and camera movement delivers film-grade imagery.
High-Fidelity Details
Realistic textures, materials, and colors produce sharp and refined visuals.
Strong Storytelling
Maintains narrative coherence and emotional depth for immersive stories.
Character Consistency
Preserves character identity and micro-expressions across long sequences.
New Capabilities of Seedance 1.5 Pro API
Doubao Seedance 1.5 Pro is a globally leading audio-visual generation model that produces highly synchronized video and audio content. It supports multi-character, multilingual dialogues, comprehensive sound generation, and start-to-end frame control, enabling cinematic storytelling for film, animation, e-commerce, and advertising.
Native Audio Generation & Precise Audio-Visual Sync
Seedance 1.5 Pro features native audio generation, producing diverse voices, ambient sounds, and spatial audio that align seamlessly with visuals for smooth and natural storytelling. It supports multiple languages and dialects, with outstanding lip-sync and motion alignment for lifelike character expression.
Cinematic Camera Control & Visual Quality
The model enables complex camera movements and professional cinematography, from expressive close-ups capturing subtle emotions to wide shots with film-level composition, lighting, and atmosphere — delivering highly consistent, detail-rich visuals.
Engaging Storytelling & Emotional Expression
Guided by prompt intent, Seedance 1.5 Pro can automatically construct narrative content while maintaining emotional and behavioral consistency across characters. It is ideal for short films, advertisements, and social media content creation.
Improvements in Seedance 1.5 Pro API Compared to Earlier Versions
Seedance 1.5 Pro is a professional-grade audio-visual generation model developed by the Doubao team. It supports unified audio-video generation and start-to-end frame control, enabling fully synchronized creation and smooth cinematic storytelling while significantly improving the efficiency and expressive power of professional video production.
| Model | 1.5-pro | 1.0-pro | 1.0-pro-fast | 1.0-lite |
|---|---|---|---|---|
Positioning | High-precision audio-video synchronization, cinematic motion and emotion, supports start-and-end frame control | Fully featured, unique multi-shot storytelling, supports start-and-end frame control | Fully featured, unique multi-shot storytelling, supports start-and-end frame control | Fully featured, unique multi-shot storytelling, supports start-and-end frame control |
Resolution | 480P, 720P, 1080P | 480P, 720P, 1080P | 480P, 720P, 1080P | 480P, 720P, 1080P |
Frame Rate | 24fps | 24fps | 24fps | 24fps |
Video Length | 4-12s | 2-12s | 2-12s | 2-12s |
Audio-Visual Generation | Supported | Not supported | Not supported | Not supported |
Text-to-Video | Supported | Supported | Supported | Supported |
Frequently Asked Questions
What is Seedance 1.5 Pro?
Seedance 1.5 Pro is ByteDance’s latest foundation video model, built on the Dual-Branch Diffusion Transformer (DB-DiT) architecture, enabling native audio-visual generation with precise lip-sync.Does Seedance 1.5 Pro allow commercial use?
Yes, content generated by the Pro version includes full commercial usage rights.Which languages does Seedance 1.5 Pro support?
The model supports multi-language audio-visual generation and lip-sync, including Mandarin, English, and Japanese.What are the maximum video duration and resolution?
Each generation supports up to 12 seconds of video at up to 1080p resolution.What input and output formats are supported?
Input supports JPEG, PNG, and WEBP images (≤10MB per file), and output is provided in standard video formats such as MP4.
