OSS Tanbou
View on GitHub

Amical — A local-first AI dictation app using Whisper and local models for offline speech-to-text

OSS health 85
About these scores

Discovery score is an unbounded weighted, log-compressed index of stars, watchers, forks, and contributors. Growth momentum is its change over the observed period; OSS health is a 0–100 score from available repository recency, Community Health, and release data.

Stars
1,531
Primary language
TypeScript
License
MIT
Repository last updated
Sep 15, 2026

Overview

Amical is a local-first dictation application that combines Whisper speech-to-text with local or open-source model processing and adapts formatting to the active application. The desktop app is built with Electron and TypeScript and currently targets macOS and Windows. The latest GitHub release checked on September 17, 2026 is v1.11.3.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Format dictation according to the active application

Amical detects whether you are writing in email, chat, an IDE, or another active app and aims to format the same speech differently for that context. Hotkeys and a floating widget make local speech input part of the normal typing workflow.

Sources: [2]

Combine Whisper and Ollama or other local models on the desktop

The README lists Whisper, Ollama, Electron, and TypeScript as core technologies. Local transcription can run without an .env file, with first-run onboarding downloading a local model.

Sources: [2]

For everyday dictation and developer writing where audio should not be sent to a cloud transcription service

It fits workflows that want local speech-to-text and optionally local-model processing for text cleanup or formatting.

Sources: [2]

Linux is not supported and roadmap items should not be mistaken for current features

Desktop local development currently targets macOS and Windows because Linux lacks the required native helper. Local Whisper transcription on macOS requires macOS 15 or later. MCP integration and real-time meeting transcription are marked as planned in the README, not shipping features.

Sources: [2]

Official sources

  1. [1]amicalhq/amical — GitHub repository metadata(2026-09-17)
  2. [2]Amical — README(2026-09-17)
  3. [3]Amical Desktop v1.11.3 release(2026-09-17)
Supplemental curator note

Separate shipping dictation capabilities from roadmap items such as MCP control and real-time meeting transcription.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/amicalhq/amical.git
  2. 2

    Enter the repository

    cd amical
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

1,531 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
62
Open PRs
15

Development activity is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • ai
  • macos
  • speech-to-text
  • whisper
  • electron
  • productivity
  • asr
  • self-hosted
  • dictation
  • mcp
  • transcription
  • ai-note-taking-app
Stars
1,531
Forks
141
Watchers
6
Open issues
43
Primary language
TypeScript
License
MIT
Repository last updated
Sep 15, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.