Buzz Captions is a desktop app for offline audio transcription and translation on your computer. It’s built on OpenAI Whisper and doesn’t require uploading recordings to the cloud, which is useful for private interviews, meetings, and podcasts.
Transcription and translation
Buzz supports speech recognition in 90+ languages, including workflows like:
- X-audio → English text
- X-audio → X-language text
- Live transcription and translation from your microphone (speed depends on your hardware and the selected model)
Files and export
You can import both audio and video files, then export finished transcripts in common formats for subtitles, editing, and further text processing:
- SRT
- VTT
- TXT
- CSV
Platforms and Whisper engines
Buzz Classic is available on Windows, Linux, and macOS (Intel). It supports multiple Whisper implementations, including:
- whisper.cpp
- Faster Whisper
This makes it easier to choose the right balance of speed and accuracy for your machine.
