Official documentation
savbell/whisper-writer: README
savbell (GitHub), 2026
Read the originalRead on October 19, 2026
- What it is
- The README of WhisperWriter, a free, open-source dictation app for Windows, macOS and Linux that uses OpenAI's Whisper model. It explains the recording modes, that text is written to the active window, the default local faster-whisper model with an optional OpenAI API, and a roadmap of unbuilt features.
- How much weight it carries
- The project maker's own repository page. The project is maintained by one author, and the README says it has had little testing. Its update notice is dated 2024-05-28, so features may have changed since. The roadmap items are read as not yet built.
Facts taken from this source
- The WhisperWriter README lists using GPT for post-processing under its roadmap, so the app does not yet rewrite or format text with AI.
“Below are features I am planning to add in the near future ... Using GPT for instructional post-processing” (README, Roadmap section)
- The WhisperWriter README says the app uses a local model by default, so speech is transcribed on the user's computer unless they switch to the OpenAI API.
“By default, the app will use a local model, but you can change this in the Configuration Options” (README, description of transcription)
- The WhisperWriter README says the transcribed text is written automatically to the active window, so it types into the app the user is working in.
“Once the transcription is complete, the transcribed text will be automatically written to the active window” (README, description of the app)