# VoiceToText

- Page: https://scanovich.ai/projects/voicetotext/
- Language: en
- Updated: 2026-11-11

- Status: released · v2.2.0
- Code: open source · MIT
- Repository: https://github.com/FUYOH666/VoiceToText
- Research line: [Private, local AI](https://scanovich.ai/research/private-local-ai.md)

Private voice typing for Apple Silicon Macs. Hold a key, speak, let go, and the text appears at the cursor.

Speech is turned into text on the Mac itself. No audio leaves the machine.

## What works today

- Local speech models on Apple's MLX: Qwen3-ASR and Whisper large-v3.
- Translation from any supported language into English.
- A local server that speaks the standard audio interface, so scripts and agents can transcribe files with the usual client library.

## Why it is in the lab

It is the daily-use proof that a private, local model can replace a hosted service for one real task. It also gives speech-to-text to the call-analytics stack.

## Evidence

- **v2.2.0 · MIT** — Public release that installs from source with one command. Measured 2026-11-11. Source: https://github.com/FUYOH666/VoiceToText

## How to engage

Setup for a team — custom vocabulary, your own models, a connection to your tools and agents.

[Contact](https://scanovich.ai/contact/) · private@scanovich.ai