# amicalhq/amical

🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.

Repository: https://github.com/amicalhq/amical
Canonical: https://ross.abutalabs.com/products/amical
Homepage: https://amical.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, macos, speech-to-text, whisper, electron, productivity, asr, self-hosted, dictation, mcp, transcription, ai-note-taking-app, dictate, dictation-tool, meeting-notes, nextjs, local-ai, ollama, windows
Last push: 2026-08-24T21:07:59+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 93, longevity 34
- inputs: {"age_days": 482, "days_push": 9, "days_rel": 46, "gap_med": 5, "n_releases_24m": 42}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1506, forks 138 (observed 2026-08-28T04:04:55.062750+00:00)

## What it is
Amical is an open-source, local-first AI dictation app for macOS and Windows that transcribes speech with Whisper and enhances it with LLMs (local via Ollama or cloud). It auto-formats dictated text contextually for the focused app and includes note-taking, custom vocabulary, and MCP integrations.

## Use cases
- dictate text instead of typing
- transcribe voice to text offline
- take meeting notes with voice
- write emails and messages by voice
- run speech-to-text locally for privacy
- dictate code comments and jira tickets

## When to choose
- you want private, offline dictation with local Whisper models
- you need context-aware formatting across different apps
- you prefer open source and self-hosted AI tooling

## When to avoid
- you need Linux or web-only dictation
- you require enterprise SSO/SAML on the free tier
- you want a fully cloud-managed transcription service

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference, mcp
- domain: speech-processing, developer-tools
- platform: windows, cross-platform
- tags: dictation, whisper, ollama, voice-to-text, local-ai, note-taking, natural-language-processing, macos, electron

## Member repositories
- amicalhq/amical (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.062750+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 2026-08-30T04:32:38.491954+00:00, confidence not recorded.
  - readme: https://github.com/amicalhq/amical (fetched 2026-08-28T04:04:55.062750+00:00, sha b560c5de9725)
  - homepage: https://amical.ai (fetched 2026-08-29T11:37:19.389339+00:00, sha f709a21b8f15)
  - site_page: https://amical.ai/docs (fetched 2026-08-29T11:37:19.398843+00:00, sha 707e5d35d1b2)
  - site_page: https://amical.ai/pricing (fetched 2026-08-29T11:37:19.401026+00:00, sha c551e6a26c6a)
  - site_page: https://amical.ai/changelog (fetched 2026-08-29T11:37:19.402903+00:00, sha a255bac2c380)
  - site_page: https://amical.ai/for/jira (fetched 2026-08-29T11:37:19.404463+00:00, sha 291d7e395e96)
- Data as of 2026-08-30T08:39:29.467469+00:00.