GraphCanon
Home/LLM Frameworks/TypeNo
TypeNo logo

TypeNo

Enrichment pending
marswaveai/TypeNo

A free, open source, privacy-first voice input app for macOS.

GitHub Website

GraphCanon updated today · GitHub synced today

877
Stars
71
Forks
3
Open issues
3
Watchers
1mo
Last push
Swift GPL-3.0Created Mar 24, 2026

Trust & integrity

Full report
Maintenance
Steady (46d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Organization account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

A free, open source, privacy-first voice input app for macOS.

Capability facts

Languages
swift

Source: github.language · Jul 11, 2026

Categories

LLM FrameworksDeveloper ToolsSpeech & Audio

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Jul 11, 2026)

- [Node.js](https://nodejs.org) (LTS recommended — install directly from nodejs.org for be
Source link

Tags

dictationproductivitylocal-firstprivacymacosmenu-bar-appaccessibilityopen-source

README

Install the speech engine

TypeNo uses coli for local speech recognition.

Prerequisites:

  • Node.js (LTS recommended — install directly from nodejs.org for best compatibility)
  • ffmpeg — required for audio conversion: brew install ffmpeg
npm install -g @marswave/coli

This installs the coli CLI itself, but it does not pre-download the speech model.

If Coli is missing, TypeNo will show an in-app setup prompt with the install command.

Node 24+: If you get a sherpa-onnx-node error, build from source:

npm install -g @marswave/coli --build-from-source

License

GNU General Public License v3.0