
Buzz transcribes and translates audio offline on your own machine, across all three desktop platforms, for free. It takes files, videos, YouTube links, and live microphone input, runs OpenAI's Whisper plus other Transformer models from Hugging Face, and accelerates on CUDA, Apple Silicon, or Vulkan. At nearly 21,000 GitHub stars it's one of the most widely used tools in this directory. It is a transcription app, not a dictation app — it won't type into your editor.
| Platforms | macOS, Windows, Linux (Flatpak and Snap), plus PyPI |
| Pricing | Free, MIT licence |
| Models | OpenAI Whisper, plus Hugging Face Transformer models of Whisper type |
| Acceleration | CUDA (NVIDIA), Apple Silicon, Vulkan |
| Inputs | Audio and video files, YouTube links, live microphone |
| Offline | Yes, entirely |
| Maturity | ~20,900 stars, 1,500 forks, 762 commits, actively maintained |
Free, MIT.
Anyone on any desktop platform with recordings to turn into text who doesn't want to pay per minute or per licence. It's the default free choice for file transcription and the only real cross-platform one. If you want to dictate into applications, this is the wrong category entirely — see Handy or superwhisper. If you want a more modern interface with summaries and more export formats, Vibe is also free.
Last verified: 9 August 2026.