OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Preencut

Preencut is a self-hosted Python application with a Gradio interface for searching audio and video files by natural-language description, analyzing speech and content, and extracting relevant clips.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Preencut — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Preencut when you have audio or video files to search for particular topics, statements or moments and want timestamped results that can be reviewed and clipped.

Who it is for

  • Editors who need to find and export specific moments from recordings.
  • Researchers and teams searching multiple media files for a topic.
  • Developers who want a documented REST API for submitting and checking media-processing tasks.

Documented uses

  • Find relevant segments in recordings using descriptive prompts.
  • Review timestamps, summaries and AI-generated tags for identified moments.
  • Re-analyze media with different prompts without reprocessing audio.
  • Export selected clips as separate files, a ZIP package or a merged video.
  • Generate SRT subtitles with timestamps and custom line length.
Before you choose

Requirements & limits

The project is available as a public GitHub repository under the MIT license and is run locally using its Gradio interface.

  • The documented workflow requires FFmpeg for video processing and API credentials for a configured LLM service.
  • The README names OpenAI Whisper for speech recognition and lets users choose a Whisper model size.
  • The application supports prompt-based re-analysis without reprocessing audio.
  • The documented REST API uses upload, task-creation and task-result routes.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and use the local Gradio interface

Install Preencut and process media through its documented web interface.

Before you start

  • Python 3.9+ is recommended.
  • Install the repository dependencies with pip.
  • FFmpeg is required for video processing.
  • Configure an LLM service in config.py and provide its API key as an environment variable.

Steps

  1. Clone the PreenCut repository and change into its directory.

  2. Install dependencies with pip install -r requirements.txt and install FFmpeg for the operating system.

  3. Configure the selected LLM service and its API key.

  4. Start the interface with python main.py, then open http://localhost:7860.

  5. Upload a supported file, choose an LLM and Whisper model, and start processing; review timestamped results and use the Cut tab to export selected segments.

Expected outcome

A local Gradio session can analyze uploaded media and provide timestamped segments for selection and export.

Guide limitations

  • The README lists support for MP4, AVI, MOV, MKV, TS, MXF, MP3, WAV and FLAC.
  • LLM service configuration and credentials are required for analysis.
  • The README documents setup and workflow but does not specify hardware requirements.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
roothch/PreenCut · Official homepage title · retained in its source language
How we review sourcesSuggest a correction