Buzz is a desktop app that transcribes speech from audio and video files into text and captions, running on your own computer. It is aimed at people who need subtitles or transcripts and want to keep their recordings private.
Whisper is a speech recognition model that turns spoken audio into text, and can also translate speech or identify the spoken language. It is aimed at developers and people who run it through the command line or Python.
A fast, offline speech-to-text engine written in C and C++ that turns recorded audio into written text on your own computer or phone. It is aimed at developers and people who want transcription without sending audio to a server.
For developers · GitHub · For developers
None of these match. Try another device.
Before you build
Planning something for an alternative to Otter.ai? See what exists first, so you can reuse parts or explain what's different. Paste this into any AI assistant:
Read the list of open-source alternatives at https://opensourceeverything.org/data/groups/transcription.json. Compare it with my project or idea below. Tell me which projects overlap, what I could reuse instead of rewriting, and what mine does that none of them do.
My project or idea:
Here is a list of open-source alternatives to Otter.ai, from Open Source Everything (CC BY-SA 4.0):
- Buzz (MIT, https://github.com/chidiwilliams/buzz; replaces fully): Buzz is a desktop app that transcribes speech from audio and video files into text and captions, running on your own computer. It is aimed at people who need subtitles or transcripts and want to keep their recordings private.
- Whisper (MIT, https://github.com/openai/whisper; replaces partly): Whisper is a speech recognition model that turns spoken audio into text, and can also translate speech or identify the spoken language. It is aimed at developers and people who run it through the command line or Python.
- whisper.cpp (MIT, https://github.com/ggml-org/whisper.cpp; replaces partly): A fast, offline speech-to-text engine written in C and C++ that turns recorded audio into written text on your own computer or phone. It is aimed at developers and people who want transcription without sending audio to a server.
Compare it with my project or idea below. Tell me which projects overlap, what I could reuse instead of rewriting, and what mine does that none of them do.
My project or idea:
