Seed Audio 1.5 teased: one prompt generates dialogue, SFX and music as separate tracks

heyronir · x · 2026-10-22

ByteDance's Seed team teases Seed Audio 1.5, which generates dialogue, emotional delivery, ambience, SFX and music from a single prompt.

Outputs will include separate tracks with precise timestamps, keeping every layer open to refinement. The same thread also shows CapCut PC's Edit Pilot: natural-language instructions to edit a selected visual element, with continuity checks on a multi-track timeline.

Original post →

More from Multimodal

• HeyGen Voice Models Take Top Two Spots on TTS Leaderboard, Turbo Free Until Nov 30 — HeyGen · 2026-10-22
• Megalith 009: stunning AI-generated megastructure concept art series — azed_ai · 2026-10-22
• Creator ships AI short film "Sky Orchard" using a custom MCP production pipeline — TinfoilTricorn · 2026-10-22
• Entire Halloween Brand Video Made With AI: CapCut Image+Video+Audio on One Timeline — JaynitMakwana · 2026-10-22
• OpenFill brings free Generative Fill to GIMP 3 via local ComfyUI, runs on old GTX cards — Speedeee_ · 2026-10-22
• Kling 4.0 Lands on Magnific: 30-Second Scenes, 10 Keyframes, Native Audio — aziz4ai · 2026-10-22

Multimodal channel →