Hold one key. Speak. Text appears — perfectly.
100% open-source • 100% local-capable • 100% free forever
email_demo_github.mp4
▶ Watch full 2-min demo on YouTube
Wispr Flow raised $81 million to build a voice dictation app.
I got annoyed, spent 3 months of late nights building my own version, and open-sourced it.
That's it.
No funding. No team. Just one stubborn developer who hates subscriptions.
This is what open source is supposed to be.
- Hold Fn → speak → release → clean, punctuated text appears anywhere
- Removes "um", "like", all fillers automatically
- Fixes grammar, can rephrase, bullet-point, or even generate text
- Tiny actions already work ("open YouTube", "set 5-min timer")
- Full Prompt Engineering: Every behavior is customizable. Tweak how Jarvis formats mail, cleans dictation, or behaves as an assistant.
- Fully offline with local Whisper (tiny/base/small)
- 100% Private, Blazingly Fast support for local LLMs via Ollama
- Or use cloud speed with Deepgram + Gemini (1M tokens/day free) — Deepgram requests default to
mip_opt_out=true
Zero tracking. Zero telemetry. Zero bullshit.
| Platform | Link |
|---|---|
| 🍎 Mac (Apple Silicon) | Download DMG (M1/M2/M3/M4) |
| 💻 Mac (Intel) | Download DMG (x64) |
| 📱 iOS (iPhone/iPad) | TestFlight (NEW!) |
✅ Signed & notarized by Apple → no scary warnings.
| Jarvis | The $700M one | |
|---|---|---|
| 💰 Price | Free forever | $10–24/month |
| 🔇 Offline / Local | Yes (Whisper) | No |
| 🔓 Open Source | Yes (MIT) | No |
| 📡 Telemetry | None | ??? |
| 👨💻 Built by | 1 guy at 2am | VC money |
- Download & open the app
- Go Local (Recommended for privacy):
- Settings → Transcription → Enable Local Whisper
- Settings → AI Models → Enable Ollama (requires Ollama installed)
- Or Go Cloud (Recommended for speed/accuracy):
- Paste free Deepgram + Gemini keys
- Hold Fn and talk
That's literally it.
Jarvis now supports running any LLM locally via Ollama. It's fast, private, and free.
- Install Ollama: Download here
- Pull a model:
# LFM2 (optimized for speed) ollama pull sam860/LFM2:1.2b # Llama 3 (standard) ollama pull llama3
- Enable in Jarvis:
- Settings → AI Models → Enable Use Ollama
- Select your model from the dropdown (Jarvis auto-detects them!)
| Shortcut | What it does |
|---|---|
Fn (hold) |
Start/stop recording |
Fn (double-tap) |
Toggle hands-free mode |
Escape |
Cancel recording |
git clone https://github.com/akshayaggarwal99/jarvis-ai-assistant.git
cd jarvis-ai-assistant
npm install && npm run build && npm run devRequires Node.js 18+, macOS 10.13+, Xcode CLI tools.
- Proper "local-only" onboarding (no fake keys needed)
- AWS Bedrock support
- Ollama support
- Custom voice commands & prompts
- Windows version
- Clipboard magic & multi-step actions
- iOS (yes, I dream big)
Open issues, vote, or drop crazy ideas → github.com/.../issues
Jarvis is a community project. If you're a developer and want to help build the future of local-first AI, check out our Contributing Guidelines.
Every star pushes this higher so more people discover they don't need another subscription.
Or just use it and tell one friend. That's enough.
Built with caffeine and spite by Akshay
Open source isn't about beating giants.
It's about making sure no one ever has to pay them.
MIT License — do whatever you want with it.