ByteDance Seed Audio 1.5 coming soon, they cooked 🔥🔥🔥.
• Generates dialogue, music, ambience and sound effects together.
• Up to six minutes of audio per generation, increased from two minutes in 1.0.
• Up to six audio references, increased from three.
• Support for 30 languages and regional variants.
• Four input modes: text; text + audio; text + video; text + audio + video.
• Video aware audio generation for dubbing and sound design around existing footage.
• Reference guided voices with instructions for emotion, style, pace and non speech vocal sounds.
• Timestamp instructions for dialogue, sound effects and music.
• Separate dialogue, ambience, effects and music tracks for editing.
@SawyerMerritt This is really amazing... I have always been a huge fan of Mark on this one, I really want them to win the XR ecosystem. I pray they get it right... But this really is very cool
I built a Photoshop-like image editor. It’s called Compositor.
https://t.co/5EMXCgaWI1
I originally built it for myself to get off my Adobe subscription, but decided to release it for free and make it open source. It has all the essential tools I need for compositing, with none of the BS.
I know this workflow is kind of archaic in 2026, but I’m still using it until AI can actually get pixel-perfect on some of the details.
The entire app is 12MB. Photoshop is 6,455MB on my machine.