3 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.
Free, open-source desktop speech-to-text app that works completely offline. Press a shortcut, speak, and the transcribed text is pasted into any text field using local Whisper or Parakeet models. Available for Windows, macOS and Linux.
OpenAI's open-source speech recognition model and command-line tool, free to download and run on your own machine. MIT licensed.
From the site: Robust Speech Recognition via Large-Scale Weak Supervision - openai/whisper
Why I recommend it: The original. Slower than whisper.cpp on a laptop, but the reference version and simple to install with Python.
A fast, dependency-light rewrite of OpenAI's Whisper speech-to-text that runs on ordinary laptop hardware, including CPU only. MIT licensed.
From the site: Port of OpenAI's Whisper model in C/C++. Contribute to ggml-org/whisper.cpp development by creating an account on GitHub.
Why I recommend it: Transcribe interviews or your own practice answers privately, without paying a per-minute transcription service.
