Helldez

On-device AI meeting assistant — real-time transcription & LLM insights, 100% offline

26
12
100% credibility
Found Apr 04, 2026 at 26 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Kotlin
AI Summary

An Android app for real-time offline speech transcription and AI insights from audio recordings using local models.

How It Works

1
📱 Discover HearoPilot

You find this handy app that turns your spoken words into text and smart notes right on your phone, keeping everything private and offline.

2
🎉 Welcome and setup

Open the app, see a friendly intro, and let it grab the speech tools it needs with a quick download so you can start listening.

3
🔽 Choose your style

Pick how you want to capture talks—like casual chats, quick meetings, long ones, or live translations—and name your session.

4
Hit record
💭
With smart notes

AI chimes in with summaries, tasks, and ideas during or after, all thought up on your device.

📝
Just words

Pure transcription without extras if you skip the smart part.

5
⏹️ Finish and review

Stop when done, see the full organized notes, edit bits, search everything, or share.

Your notes are ready

Enjoy searchable, editable records of meetings and talks that stay private on your phone forever.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 26 to 26 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is HearoPilot-App?

HearoPilot-App is a Kotlin Android app delivering on-device meeting transcription and real-time LLM insights as a 100% offline assistant. It captures audio via local speech-to-text, generates summaries, tasks, and translations across four modes—from simple listening to long meetings—without cloud dependency. Users get searchable session history, editable transcripts, and screen-off recording in 25 languages.

Why is it gaining traction?

It stands out with privacy-first design: no data leaves the device, yet delivers smooth real-time transcription and contextual AI on mid-range phones. Features like resumable model downloads, global full-text search with highlights, and adaptive LLM quantization avoid common pitfalls like "no space left on device" errors in GitHub Actions runners. Devs dig the battery-friendly thermal throttling and post-stop insight generation.

Who should use this?

Android devs prototyping offline AI tools, mobile teams building enterprise meeting apps, or indie hackers needing local transcription for sensitive calls. Suited for Kotlin experts integrating Sherpa-ONNX STT and llama.cpp LLM, or anyone ditching cloud services for on-device workflows.

Verdict

Worth forking for on-device meeting transcription demos (26 stars, 1.0% credibility signals early stage), with strong README but watch model storage for "no space left on device" GitHub workflow snags. Solid base if offline LLM is your hook—test on real hardware first.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.