What is jevcut and what does it produce?

A CLI auto-clipper that transcribes a long video, finds moments worth clipping, decides where each clip starts and ends, drops anything that does not stand alone or turns out to be an ad, and writes ranked mp4s for Shorts, Reels or TikTok.

How does Jev choose clip boundaries?

It never picks raw timestamps. Code enumerates every plausible start and end — sentence ends, pauses and speaker changes — and Jev judges the clip each candidate edge would make or picks among candidates code already listed.

How was jevcut evaluated?

On 38 hand-labelled videos across 13 genres it beat five simpler approaches — sentence scoring, fixed windows, padding the top sentence, and two code-set-edge variants — on recall, edge placement and precision, in the project's own BENCHMARKS.md.

What does it cost to clip an hour of video?

The README estimates about 3¢ of Jev per hour of video, with transcription billed separately through whichever model you choose (the example uses lemonfox). Costs scale with the video's length, not the number of clips.

What kinds of videos can jevcut handle?

v1 clips verbal content: podcasts, interviews, talks, panels, comedy and streams where people talk. A moment carrying no words — a crash, scream or stunt — is invisible because the judge reads the transcript.

One command: uv run jevcut run talk.mp4 --model lemonfox. It writes ranked mp4s plus a page to watch them on, best first. The repo is MIT-licensed Python, created 2026-09-20 with a roadmap and an issues directory.

How is it different from other Jev-based clippers?

The README compares boundary methods: jevmeter finds energy over rolling averages, jev-skip snaps 30s windows to sentence ends, and youtube-sponsor-detection's scan-anchor-trace idea is credited and generalized here. jevcut's bet is candidates in code, judgment in Jev.

Jev directory

CommunityJev Tools & CLIs

Jevcut

An auto-clipper that turns long videos into short standalone clips: code enumerates every plausible cut point, Jev judges the clip each candidate edge would make, and you get ranked mp4s for Shorts, Reels and TikTok.

See highlights Open github.com

Stars: 4
Language: Python
License: MIT
Reading time: 2 min
Published by: Community
Author: vbs2004
Last verified: Oct 2026

vbs2004/jevcut

User repository on GitHub

View on GitHub

Auto-clipper that turns long videos (podcasts, talks, essays, comedy) into short standalone clips for Shorts, Reels and TikTok. Code lists every possible cut; an AI judge picks where each clip starts and ends. Benchmarked on 38 hand-labelled videos.

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity catalog-import logicrw video cli

Works forJev for Ranking Jev for Scoring

Used inJev for Media & Entertainment

Languages: Python
Platforms: CLI
Capabilities: Open sourceRequires API key

Highlights

Code lists every plausible cut — sentence ends, pauses ≥350ms, speaker changes — and Jev never names a timestamp, only judges clips.
Benchmarked on 38 hand-labelled videos across 13 genres, it beat five simpler approaches on recall, edge placement and precision.
The README estimates about 3¢ of Jev per hour of video; the demo cuts 62 clips from a 97-minute podcast, with transcription extra.
v1 clips verbal content only: the judge reads transcripts, so a crash, scream or stunt with no words is invisible to it.
Design history: Choice-picked cuts matched a constant offset, and code-placed edges dropped 57% of labelled moments.

Quickstart

bash

uv run jevcut run talk.mp4 --model lemonfox

Watch out

Copy reviewed against the truncated repo README on 2026-10-15; the capture ends inside the 'what jevcut does differently' section, so the rest of the benchmark and cost sections were not reviewed. All performance figures are the project's own self-published results, and the README says edges remain the weak point.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Jevcut

Highlights

Quickstart

Questions about this entry

What is jevcut and what does it produce?

How does Jev choose clip boundaries?

How was jevcut evaluated?

What does it cost to clip an hour of video?

What kinds of videos can jevcut handle?

How do I run jevcut?

How is it different from other Jev-based clippers?

More Jev resources like this

From the Jev guides

From the Jev AI model community