Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Typeflux is a macOS menu bar voice input tool built with Swift. It is designed for a fast "hold to talk, release to insert" workflow: press a hotkey, speak naturally, let the app transcribe your speech, and send the resulting text back into the currently focused app.
| Date | Stars |
|---|---|
| 2026-07-24 | 322 |
| 2026-07-25 | 322 |
| 2026-07-28 | 323 |
| 2026-07-30 | 328 |
| 2026-08-06 | 328 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # [Typeflux](https://typeflux.app) - Talk. We'll Type. Hold `Fn` to dictate, or double-press `Fn` to ask anything. Typeflux delivers lightning-fast, accurate voice-to-text directly into any macOS application. Free, open-source, and supports local models — your voice never has to leave your Mac. [](https://github.com/mylxsw/typeflux/actions/workflows/test.yml) [](https://codecov.io/gh/mylxsw/typeflux) English | [简体中文](./README.zh-CN.md) [](https://youtu.be/ZxWWUOEgaJ4)  [View more screenshots](./docs/SCREENSHOTS.md) </div> ## Download **[⬇ Download latest release (.dmg)](https://github.com/mylxsw/typeflux/releases/latest)** 1. Download `Typeflux.dmg` from the latest release 2. Open the DMG and drag `Typeflux.app` to **Applications** 3. Launch and grant Microphone + Accessibility permissions > **macOS 13+** · Free · No subscription · Fully local inference supported ## Why Typeflux Most voice input tools force you to switch apps — dictating in one place, then copying and pasting into another. That context switch breaks flow. Typeflux injects text directly into whichever app you're already using, at the cursor position, the moment you release the hotkey. It feels like typing, just **4× faster** (~200 WPM vs. ~50 WPM). And when you need more than dictation, **Ask Anything** turns your voice into an AI assistant for Q&A, rewriting, translation, and complex workflows. ## How It Works ``` Hold Fn → Speak → Release → Text appears instantly Fn ×2 → Ask → Release → Answer, edit, or action ``` 1. **Press and hold** `Fn` (default hotkey) 2. **Speak naturally** 3. **Release** — Typeflux transcribes and injects the text at your cursor 4. **Double-press** `Fn` to use Ask Anything for Q&A, selected-text edits, and agent workflows 5. The result is also copied to clipboard as a fallback ## Features ### One-Click Voice Input Hold `Fn` to start, release to stop. No switching input methods, no clicking buttons — works in any text field across browsers, code editors, terminals, and native apps. ### Ask Anything (`Fn` ×2) More than just dictation. Double-press `Fn`, speak on the second press, then release to chat with an AI agent using your voice: - **Voice Q&A** — Ask questions and get instant answers - **Content Rewrite** — Select text, then speak an instruction like "make this shorter" or "translate to English" - **Complex Workflows** — Handle multi-step tasks through natural conversation ### Local-First, Privacy-First Run entirely on your Mac with on-device models. No API keys needed, no data leaves your machine. We don't collect, store, or analyze any of your voice or text data. ### Custom Personas Create named instruction sets for different scenarios — work emails, study notes, casual chat, code comments — and switch between them from the menu bar. ### Multiple Speech Backends | Provider | Type | Best For | |----------|------|----------| | Typeflux Cloud | Cloud | Zero-config, balanced accuracy | | Local Model | Local | Privacy, offline use | | Alibaba Cloud ASR | Cloud streaming | Low latency, Chinese | | Doubao Realtime ASR | Cloud streaming | Chinese optimization | | Google Speech-to-Text | Cloud | Multi-language, enterprise | | OpenAI (Whisper API) | Cloud | High accuracy | | Multimodal LLM | Cloud | Vision + audio tasks | | Groq | Cloud | Fast inference, low cost | | Free Models | Cloud | No API key, open-source endpoints | ### Local Models When you choose **Local Model**, Typeflux downloads and runs the model entirely on your Mac: | Model | Size | Params | Best For | |-------|------|--------|----------| | SenseVoice | ~350 MB | 234M | Fast multilingual, strong Mandarin/Cantonese/English/Japanese/Korean | | FunASR (Paraformer) | ~180 MB | 2
Excerpt of 6,596 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:563cc04af124b5bb, topic:voice-assistant, readme:speech-to-text