Audio and video · Independent · 22 Oct 2026

thewh1teagle/vibe

Transcribe on your own!

← Audio and video
Vibe: offline transcription. Turns audio and video into text on your device.

In simple English

Vibe is a desktop program that turns spoken words in audio and video files into written text. It runs entirely on your own computer, so your voice recordings never leave your device and are never sent to a cloud server. You do not need any coding skills or an internet connection to use it once installed. It supports dozens of languages and saves your transcripts in many common file formats. The software is free to download and use.

What it is

Vibe is an open-source desktop application built with Rust and TypeScript that uses local speech-to-text models like Whisper to transcribe media files offline. It features a graphical interface, hardware acceleration for graphics cards, batch processing, and optional local AI integration via Ollama.

What it is good for

Anyone who needs to turn meetings, interviews, podcasts, or video clips into written text without paying for a cloud service or risking privacy. It suits creators, researchers, and journalists who want to process sensitive audio files entirely on local hardware.

Stars7.9k
LicenceMIT
Latestv3.2.2 (2026-09-05)checked 22 Oct 2026
Last code change2026-10-06
Written inTypeScript
Setup effort
1 / 5
Payoff
5 / 5
Good
  • Runs completely offline to keep all your voice recordings private.
  • Supports batch processing for multiple audio and video files at once.
  • Exports transcripts into standard formats like SRT, VTT, TXT, PDF, and DOCX.
Watch for
  • Requires a computer with a decent graphics card or plenty of RAM to transcribe quickly.
  • Downloading and setting up large speech models takes up significant disk space.
  • Large video files or long recordings can take considerable time to process on older hardware.
Replaces

paid cloud transcription services

Works well with

Ollama

Similar repositories
  • openai/whisper111k stars

    The underlying command-line speech recognition model that powers many local transcription tools.

  • ggml-org/whisper.cpp55k stars

    A lightweight C and C++ port of the Whisper model designed for fast local execution.

Also reviewed on Repo Radar
  • mpv-player/mpv38k stars

    A command-line media player that handles most audio, video and subtitle formats and can be driven entirely from scripts.

  • snapcast/snapcast8.0k stars

    A server and clients that play one audio stream in several rooms, kept in time with each other.

  • MusicPlayerDaemon/MPD2.8k stars

    A background music player with no interface of its own, controlled over a network by separate client programs.

How to get it

Download the installer directly from the project website at https://thewh1teagle.github.io/vibe/ and run it on your operating system.

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: Design & Creative › Audio & Voice Production › Transcription.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.