In the open

What's shipped, and what's next

Nasar Flow is built in the open, so here's exactly where things stand. No fixed dates, just an honest status: this is a solo indie project, built without a Mac, shipped through GitHub Actions.

Shipped

Live in the beta today
Fully on-device transcription

Runs on whisper.cpp. Nothing is ever uploaded.

Singlish & English model

The default model, tuned on real Singlish speech.

Malay support

Everyday Bahasa, not just formal Malay.

Arabic model (beta)

Colloquial (Amiyah) Arabic, including common Islamic phrases.

Auto language routing

Detects which language you're in and picks the right model.

Private TestFlight beta

Invite-only, automatically, straight from this site.

In progress

Being actively worked on
Arabic accuracy

The current model is workable but genuinely imperfect. Improving it is the top priority.

Smarter language detection

Today it's rule-based keyword matching. A trained classifier is next.

Planned

On the list, not started
Learned voice detection

Replacing simple energy-threshold silence detection with a proper VAD model.

Resumable downloads

Model downloads should survive a force-quit mid-transfer, not just a backgrounded app.

Public App Store release

Once the beta has proven itself out with real feedback.

Have a request?

See something missing?

Open an issue on GitHub, it's the fastest way to reach me directly.

Open an issue on GitHub