@Ryrenz: Damn, you can find the clip you want from hours of footage with just one sentence — MIT License, Whisper transcription plus LLM analysis. The most painful part of editing long videos is finding footage. With hours of recordings, to find every segment about a topic, you can only drag the timeline and listen bit by bit, burning an entire afternoon. PreenCut ...

X AI KOLs Timeline Tools
video-editing whisper llm open-source search-tool transcription

Summary

PreenCut is an open-source tool (MIT License) based on Whisper transcription and LLM analysis, allowing users to search for segments in long videos using natural language, with support for batch processing, export/merging, and a REST API.

Damn, you can find the clip you want from hours of footage with just one sentence. MIT License, Whisper transcription plus LLM analysis. The most painful step in editing long videos is finding footage. With hours of recordings, to find all the segments where a certain topic is discussed, you can only drag the timeline and listen bit by bit, and an afternoon is gone. PreenCut turns this into search: first use Whisper to transcribe the audio to text, then have an LLM analyze, segment, and summarize it; after that you just search with natural language. The found clips can be exported or merged, and SRT subtitles can be generated too. Batch processing and re-analysis are both supported. It supports a wide range of formats: video like mp4, avi, mov, mkv, ts, mxf, plus audio like mp3, wav, flac, powered by FFmpeg underneath. The interface includes a Gradio web version, and a REST API is also provided to integrate into your own workflows. Only when footage can be searched does editing finally enter the modern era. GitHub:
Original Article
View Cached Full Text

Cached at: 08/12/26, 12:25 PM

Whoa — you can find the exact clip you want from hours of footage with just one sentence.

MIT license, Whisper transcription plus large-model analysis.

The most painful part of editing long videos is finding footage. With hours of recordings, if you want to pull out every clip that mentions a certain topic, you’re stuck dragging the timeline and auditioning segments one by one — there goes an afternoon.

PreenCut turns this into a search: first it uses Whisper to transcribe audio into text, then a large model analyzes, segments, and summarizes it. After that, you just search in natural language. The clips you find can be exported or merged, and SRT subtitles can be generated too. Batch processing and re-analysis are both supported.

It eats a broad range of formats — video like mp4, avi, mov, mkv, ts, mxf, plus audio like mp3, wav, flac — all powered by FFmpeg underneath. The UI comes as a Gradio web app, and there’s also a REST API for hooking into your own pipeline.

Once your source material can be searched, editing has finally entered the modern era.

GitHub:

Similar Articles

@Smartpigai: Every time someone asks me 'What tools do you use for content / video / material management?', I can't be bothered to explain again. Here's a one-time comprehensive list — save it yourself: 1. Video editing (make videos with code) https://github.com/remotion-dev/remotion… 2. Speech-to-text / meeting minutes…

X AI KOLs Timeline

A post compiling multiple open-source tools for content creation, including video editing, speech-to-text, AI drawing, media processing, etc., emphasizing free and open-source and the ability to build your own system.

@XAMTO_AI: What’s the most annoying part of making short videos? For me, it’s endlessly searching for footage, syncing timelines, and adjusting subtitles. A recently came across an open-source tool called MoneyPrinterTurbo (100k+ Stars) that strings these steps into an automated pipeline. The logic is pretty direct: enter a topic or keyword, and the system calls a large model to generate…

X AI KOLs Timeline

This article introduces MoneyPrinterTurbo, an open-source tool that automatically handles script generation, footage matching, voiceover, subtitles, and background music for short videos by inputting a topic or keyword, with support for multiple large models and voice APIs.

@bkdgiffug: What’s the biggest fear in short-video creation? Originality runs dry, reposting gets throttled — both avenues are dead ends. This open-source tool helps you break the deadlock with AI-powered batch remixing. Short-Video-Factory simplifies it to three steps: write prompts, drop storyboard materials, wait for finished output. Copywriting, voiceover, editing, and subtitles are automated end-to-end. Local processing keeps data secure, W…

X AI KOLs Timeline

Short-Video-Factory is an open-source cross-platform desktop tool that automates short-video remixing with AI. It supports copywriting generation, speech synthesis, editing, and subtitles, and enables batch processing to improve creative efficiency.

@mogician301: https://x.com/mogician301/status/2072250774332285073

X AI KOLs Timeline

Introduces an open-source tool called audio-to-text that uses AI and local tools (like faster-whisper and ffmpeg) to help users automatically generate, proofread, and burn subtitles, solving problems such as high costs, frequent errors, and cumbersome workflows in software like CapCut.

@Sixtimenight: https://x.com/Sixtimenight/status/2086079773793833216

X AI KOLs Timeline

Introducing a Jianying short-video mass-production workflow: use Codex to copy existing manually tuned templates, operate Jianying drafts via VectCutAPI and jianying-editor-skill, and replace one-by-one generation from scratch, enabling batch production and automated publishing.