# voquill/voquill

Open source voice dictation technology

Repository: https://github.com/voquill/voquill
Canonical: https://ross.abutalabs.com/products/voquill
Homepage: https://voquill.com/dictation
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: agent, agentic-ai, dictation, free, local-ai, open-source, speech-to-text, tauri, whisper, voquill
Last push: 2026-08-01T16:18:47+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 95, release rhythm 83, longevity 24
- inputs: {"age_days": 345, "days_push": 32, "days_rel": 32, "gap_med": 0, "n_releases_24m": 156}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1008, forks 124 (observed 2026-08-28T04:03:12.632491+00:00)

## What it is
Voquill is an open-source, cross-platform AI voice dictation app that lets users dictate into any desktop application, with AI-powered transcript cleanup and a personal glossary. It supports local Whisper transcription (with optional GPU acceleration), bring-your-own API key cloud providers, and fully offline operation.

## Use cases
- dictate text into any app with my voice instead of typing
- run speech-to-text locally offline for privacy
- transcribe voice with whisper on my desktop
- clean up filler words from voice transcripts with AI
- add custom vocabulary so names are spelled correctly in dictation
- voice typing that works system-wide on mac windows and linux
- voice-powered AI assistant chats

## When to choose
- you want private, offline-capable voice dictation that never sends audio to the cloud
- you need system-wide dictation across macOS, Windows, and Linux
- you want to choose between local Whisper and cloud transcription providers
- you need custom glossary terms and writing styles for dictation

## When to avoid
- you need mobile-only dictation (desktop is the primary target)
- you require a fully managed enterprise transcription service without self-hosting
- you need speaker diarization or meeting transcription features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, gui
- domain: speech-processing, developer-tools, artificial-intelligence, cross-platform
- platform: windows, cross-platform
- tags: voice-dictation, whisper, tauri, speech-to-text, local-ai, text-cleanup, personal-dictionary, privacy-first, macos, linux, desktop

## Member repositories
- voquill/voquill (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:12.632491+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 2026-08-30T07:12:22.400303+00:00, confidence not recorded.
  - readme: https://github.com/voquill/voquill (fetched 2026-08-28T04:03:12.632491+00:00, sha 5d253a05d98e)
  - homepage: https://voquill.com/dictation (fetched 2026-08-29T13:12:25.983653+00:00, sha 5366fb64b3b0)
  - site_page: https://docs.voquill.com (fetched 2026-08-29T13:12:25.986806+00:00, sha 574c038db30e)
- Data as of 2026-08-30T08:39:29.467469+00:00.