# savbell/whisper-writer

💬📝 A small dictation app using OpenAI's Whisper speech recognition model.

Repository: https://github.com/savbell/whisper-writer
Canonical: https://ross.abutalabs.com/products/whisper-writer
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: openai, whisper, dictation, speech-recognition, speech-to-text, typing-assistant, faster-whisper, openai-api, openai-whisper
Last push: 2024-08-24T20:31:15+00:00

## Health v2 (maintenance only)
Score: 20/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 88
- inputs: {"age_days": 1233, "days_push": 739, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1097, forks 197 (observed 2026-08-28T04:03:34.685641+00:00)

## What it is
WhisperWriter is a small desktop dictation app that transcribes microphone audio to text using OpenAI's Whisper model, either locally via faster-whisper or through the OpenAI API. It runs in the background, activates via a keyboard shortcut, and types the transcribed text into the active window.

## Use cases
- dictate text into any application with a hotkey
- transcribe my voice to the active window using whisper locally
- voice typing assistant for hands-free writing
- speech-to-text dictation without sending audio to the cloud
- press a shortcut to record and auto-type what I say

## When to choose
- you want hotkey-driven dictation that types directly into any app
- you prefer local transcription with faster-whisper for privacy
- you want configurable recording modes like continuous or hold-to-record

## When to avoid
- you need batch transcription of audio files rather than live dictation
- you need a mobile or web-based dictation solution
- you require enterprise-grade reliability or extensive accessibility features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, gui
- domain: speech-processing, developer-tools
- platform: cross-platform, python
- tags: whisper, dictation, speech-to-text, voice-typing, faster-whisper, pyqt5, natural-language-processing, desktop

## Member repositories
- savbell/whisper-writer (main) score 20

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.685641+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:46:37.065076+00:00, confidence not recorded.
  - readme: https://github.com/savbell/whisper-writer (fetched 2026-08-28T04:03:34.685641+00:00, sha a5bcd6e77463)
- Data as of 2026-08-30T08:39:29.467469+00:00.