Seedance 1.5 Pro

• 🏢 ByteDance's flagship Seedance video family, text-to-video generation
• 🆕 Joint audio-video model following complex instructions
• 💬 Native lip-sync, spatial sound, many languages and dialects
• 🎯 Complex camera movement, from close-ups to wide shots
• 👁️ Diverse voices and spatial sound effects coordinated with visuals
• 🌐 Part of ByteDance's broader Seed video and image lineup
• 🔒 Proprietary license; available via third-party APIs

ByteDance

ByteDance is a Chinese internet technology company headquartered in Beijing, widely known as the parent company behind TikTok and Douyin. Beyond social media, ByteDance has invested heavily in artificial intelligence research, building generative media models…

Seedance 1.5 Pro is the text-to-video member of ByteDance's flagship Seedance line, marketed for realistic motion, scene consistency, and what the provider describes as cinematic visuals. According to ByteDance's Seed team, it is a joint audio-video model that accurately follows complex instructions, generating diverse voices and spatial sound effects coordinated with visuals, with support for a wide range of languages and dialects alongside lip-sync and motion alignment. It is also designed for complex camera movement, from close-ups capturing subtle facial expressions to wide shots with cinematic composition and atmosphere.

A defining feature of the 1.5 series is native audio-visual generation: per ByteDance's Seed team, the model produces synchronized voices, spatial sound, and motion-aligned audio rather than requiring separate audio post-production.

Within the family, ByteDance also offers an image-to-video variant, Seedance 1.5 Pro, and a newer generation, Seedance 2.0, with faster and mini editions such as Seedance 2.0 Fast and Seedance 2.0 Mini. The line sits alongside ByteDance's Seedream image models. The model is proprietary and reached this catalog via API access; usage is subject to ByteDance terms.