Building an AI Sound Design Pipeline Inside DaVinci Resolve | BC+AI Film Club April 2026
· 5:23
What if you could generate 70 tracks of sound design from a single video file — and drop them into your timeline timecode-accurate? Kevin Friel spent his spare…
Notes & highlights
Published: · 5:23
What if you could generate 70 tracks of sound design from a single video file — and drop them into your timeline timecode-accurate?
Kevin Friel spent his spare time vibe-coding exactly that. His custom pipeline combines three APIs — DaVinci Resolve, Google Gemini, and Eleven Labs — to analyze video, generate creative sound design prompts inspired by legends like Ben Burtt and Gary Rydstrom, then automatically place Foley, atmos, and ambience where they belong.
• DaVinci Resolve API + Gemini vision analysis + Eleven Labs audio generation
• Scans video, crafts context-aware sound prompts, generates multi-layer audio
• Auto-imports into DaVinci with correct file names, bins, and timecode
• First pass often delivers 70+ layers — 30% duds, but the richness is there from the start
• DaVinci Resolve Studio's native AI auto-mixer for initial audio mixing
--------
💥 Join the movement
Join BC + AI: https://bc-ai.ca/membership/
Next Vancouver AI meetup: https://luma.com/vancouver-ai
Smash that Subscribe & 🔔 so you don't miss future Spotlights.
Drop a comment: Would you trust AI for your first pass of sound design?
Share the vid with a post-production nerd who loves automation.