Note: Seedance 1.5 Pro is ByteDance's next-generation audio-visual generation model, officially released in December 2025. Learn more in the official release announcement and model homepage.
We've added Seedance 1.5 Pro as a video model for joint audio-visual generation. Create videos with synchronized sound and vision in a single pass—no separate dubbing or audio workflow needed.
About Seedance 1.5 Pro
Seedance 1.5 Pro is ByteDance's flagship audio-visual model, built for text-to-video and image-to-video with native sound generation. Our integration brings the following benefits:
- Sound and Vision in One Take: Joint audio-visual generation—dialogue, music, and sound effects are created alongside the video, perfectly synchronized.
- Precise Lip-Sync: High audio-visual alignment for lip movements, intonation, and performance rhythm. Natural, expressive voices.
- Multilingual Support: Native support for multiple languages and dialects—Chinese, English, Japanese, Korean, Spanish, Indonesian, and regional accents (e.g., Sichuanese, Cantonese).
- Cinematic Camera Control: Complex camera movements such as dolly zooms, continuous long takes, panning, and professional scene transitions.
- Narrative Coherence: Strong semantic understanding for storytelling—films, ads, short dramas, anime, and gaming content.
What's New
- Seedance 1.5 Pro: A new video model for text-to-video and image-to-video with built-in audio. Available in the video model selector.
How It Works
Select Seedance 1.5 Pro in your video model settings when creating videos. The model generates both visuals and audio together—ideal for dialogue-driven content, explainers, ads, short dramas, and cinematic storytelling. Use text prompts or start from an image; the model handles the rest.
Learn more about Seedance 1.5 Pro and the ByteDance Seed family at seed.bytedance.com.