Buzz Features
- Real-time transcription and translation from your computer’s microphone to text. Transcribe as you speak.
- Import audio and video files and export transcripts to TXT, SRT and VTT. You can add mp3, mp4 and more audio and video formats.
- Compatible with Whisper, Whisper.cpp and Hugging Face compatible with Whisper.
How to install Buzz
Buzz is available for Mac and Windows. On the download page (linked above), you can download the .DMG for Mac or the .EXE for Windows. Once downloaded, it’s as simple as following the usual software installation process and you’re done, no hassle.
On the left we see the work queue. Audio and video files can be added to start transcribing the text. On the right we see the result of the transcription in different formats: “TXT”, “SRT”, “VTT”.
Understanding the program
| Field | Options | Description |
|---|---|---|
| Task | “Transcribe”, “Translate” | “Transcribe” c converts the input audio to text in the selected language, while “Translate” converts it to English. |
| Language | See Whisper documentation for a complete list of supported languages | “Detect Language” will attempt to detect the language spoken in the audio from the first few seconds. It is recommended to select a language (if known) as it will improve the quality of the transcription in many cases. |
| Quality | “Very low”, “Low”, “Medium”, “High” | The quality of the transcription determines the Whisper model used for transcription. “Very low” uses the “tiny” model; “Low” uses the “base” model; “Medium” uses the “small” model; and “High” uses the “medium” model. |
As you can see, the interface is simple. It has changed in the last updates, adding the function to queue different files. This has been a stroke of genius that allows us to add a long task queue to let the AI work for hours non-stop on a packet of audio or video files.
0 Comments