Skip to main content
Join Waitlist
Passcut BlogPasscut Core Team

Frame-Accurate Rough Cuts Explained — Passcut

How Passcut combines probabilistic LLM transcript selection with deterministic silence snapping for exact timecode cuts.

Published:
Last Updated:

How Passcut achieves frame accuracy with AI

Passcut’s hybrid editing engine pairs Apple Foundation Models for transcript text selection with a deterministic C/Swift audio engine that snaps cut boundaries to silence intervals and video frame edges.

This architecture prevents the cut drift, clipped audio syllables, and frame misalignments inherent in pure generative AI video tools.

Native macOS • On-Device AI

Test Frame-Accurate AI Rough Cuts

Join the Passcut waitlist for Apple Silicon Macs.

Requires macOS 26 or later and Apple Silicon. No cloud processing, zero spam.

#Frequently Asked Questions

Why can't language models generate timecodes directly?

Language models generate text probabilistically and hallucinate mathematical timecode offsets. Passcut uses LLMs only for text selection, using a deterministic engine for exact cut calculations.

Native macOS • On-Device AI

Get Early Access to Passcut

Passcut is currently in pre-launch. Join the waitlist to receive early access as soon as the native macOS build is ready.

Requires macOS 26 or later and Apple Silicon. No cloud processing, zero spam.