# TypeWhisper/typewhisper-mac

Local speech-to-text for macOS  on-device AI, fully private, optional cloud

Repository: https://github.com/TypeWhisper/typewhisper-mac
Canonical: https://ross.abutalabs.com/products/typewhisper-mac
Language: Swift
License: GPL-3.0
License Family: copyleft
Topics: apple-silicon, dictation, macos, on-device, privacy, speech-to-text, swiftui, transcription, whisper, whisperkit
Last push: 2026-08-26T08:57:36+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 14
- inputs: {"age_days": 202, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 453}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1735, forks 125 (observed 2026-08-28T04:05:29.039012+00:00)

## What it is
TypeWhisper is a macOS application for local, on-device speech-to-text dictation built on WhisperKit, with optional cloud transcription via Groq, OpenAI, or xAI. It also supports AI text transformation through reusable workflows, hotkeys, recording history, and meeting automation.

## Use cases
- dictate text on mac without sending audio to the cloud
- transcribe voice memos locally with whisper
- convert speech to text using hotkeys on macOS
- transcribe audio files with on-device AI
- post-process transcriptions with AI workflows
- private voice dictation for apple silicon macs

## When to choose
- you want fully private, on-device dictation on macOS 14+
- you have an Apple Silicon Mac and want fast WhisperKit transcription
- you want optional cloud providers with local-first fallback
- you need AI-powered text transformation of dictated text

## When to avoid
- you need speech-to-text on Windows or Linux
- you need a cross-platform or CLI-only transcription tool
- you require GPL-incompatible licensing in your product

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, llm-inference, workflow-automation
- domain: speech-processing, developer-tools, privacy, apple-ecosystem
- platform: -
- tags: whisper, whisperkit, dictation, on-device-ai, swiftui, transcription, voice-to-text, macos

## Member repositories
- TypeWhisper/typewhisper-mac (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:29.039012+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 2026-08-30T03:30:45.935211+00:00, confidence not recorded.
  - readme: https://github.com/TypeWhisper/typewhisper-mac (fetched 2026-08-28T04:05:29.039012+00:00, sha 214071f00196)
- Data as of 2026-08-30T08:39:29.467469+00:00.