Buzz

Transcribe and caption audio offline on your computer.

Editorially reviewedChecked Oct 2026How we review·19 visited this week

transcription#practical-oss#open-source#self-hosted#transcription

Visit Website

Free plan Self-hosted Offline mode

Toolglade’s take

A straightforward, privacy-friendly way to run Whisper transcription locally with a real GUI instead of the command line, and the permissive MIT license is a bonus. It is best for people who regularly transcribe interviews, lectures, or media offline; those who need occasional transcription may prefer a hosted service, and anyone on older or low-end hardware should expect slower runs with the larger, more accurate models.

Should you use Buzz?

Biggest strength: Runs fully offline on your own machine, keeping audio private
Biggest weakness: Accuracy and speed depend on the Whisper model size and your hardware; larger models need a capable GPU
Pricing: Free plan
Top alternative: Wordtake · see all

Facts & pricing last checked October 2026. How we review

About Buzz

Buzz transcribes and translates audio and video into text entirely offline, powered by Whisper. It is a free, private way to caption recordings without sending them to the cloud.

Buzz is a free desktop app that transcribes and translates audio offline on your own computer, powered by OpenAI's Whisper models. You can import audio or video files (or YouTube links), transcribe live from a microphone in real time, and export the results as TXT, SRT, or VTT subtitle files. It also offers a transcription viewer with search and playback controls, speaker identification, a watch-folder for automatic processing, and a command-line interface for scripting. It is MIT-licensed and available for Windows, macOS, and Linux. Because everything runs locally, Buzz is a good fit for journalists, researchers, students, podcasters, and subtitlers who want privacy or need to work without an internet connection. It supports multiple Whisper backends with hardware acceleration: CUDA for Nvidia GPUs, Apple Silicon support on Macs, and Vulkan via Whisper.cpp on many other GPUs. Accuracy and speed depend heavily on which model size you choose and the hardware you run it on.

Weighing your options?See how Buzz compares to the alternatives.

Pros & cons

Pros

Runs fully offline on your own machine, keeping audio private
Permissive MIT license
Handles files, YouTube links, and live microphone transcription
Exports to TXT, SRT, and VTT, with speaker identification and a watch-folder option
Hardware acceleration via CUDA, Apple Silicon, and Vulkan for faster processing

Cons

Accuracy and speed depend on the Whisper model size and your hardware; larger models need a capable GPU
Whisper's translation feature outputs English, so it is not a general any-to-any translator
Installers are unsigned, so Windows and macOS show security warnings on first run
Intel Macs are no longer supported beyond an older release; current versions require Apple Silicon