Intent-Lab

Intent-Lab / GlassFlow

Public

Real-time transcription and AI assistant for Meta Ray-Ban smart glasses. Live speech-to-text, speaker diarization, Gemini Live vision+voice, and WebRTC streaming.

46
5
100% credibility
Found Mar 16, 2026 at 46 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

GlassFlow is a mobile app for iOS and Android that provides real-time speech-to-text transcription from Meta Ray-Ban smart glasses or phone microphones, including speaker identification and optional AI assistance.

How It Works

1
🔍 Discover GlassFlow

You hear about GlassFlow, a handy app that turns conversations from your smart glasses into live text captions right on your phone.

2
📱 Get the app on your phone

Download and open the app on your iPhone or Android phone using your computer's coding tool, then pick your device to run it.

3
🔑 Connect captioning service

Sign up for a free live captioning service online and add your private access code in the app's settings so it can understand speech.

4
Choose your audio source
📞
Phone only

Tap start on phone to test transcription with your phone's mic and camera.

🕶️
With smart glasses

First enable a special feature in the glasses companion app, then tap start streaming in GlassFlow.

5
🎤 Tap Scribe to transcribe

Press the big Scribe button and start talking – watch words appear live on screen with labels for each speaker.

6
💬 See real-time captions

As people speak, partial words fill in instantly, then full sentences with punctuation scroll by smoothly.

✅ Perfect conversation records

Now you have clear, labeled transcripts of every chat, hands-free from your glasses or phone anytime.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 46 to 46 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 GlassFlow?

GlassFlow delivers real-time transcription for Meta Ray-Ban smart glasses through iOS and Android apps built in Swift and Kotlin. It streams audio from glasses or phone mics to Deepgram's API for live speech-to-text, speaker diarization labeling speakers as S1 or S2, and partial results that update as you speak. Developers get Gemini Live for voice-plus-vision AI chats and WebRTC streaming to share glasses POV in a browser—ideal for hands-free note-taking in conversations.

Why is it gaining traction?

Unlike generic real-time transcription APIs on GitHub, GlassFlow hooks into Meta glasses developer mode for seamless Bluetooth audio capture, with phone fallback for testing. Real-time dashboard-like transcripts with punctuation and diarization beat basic STT tools, and WebRTC adds live video sharing without extra setup. It's a ready real-time project for wearables, standing out amid python real-time transcription experiments or Azure endpoints.

Who should use this?

Mobile developers prototyping AR apps for smart glasses, accessibility specialists building live captioning for meetings, or field reporters needing instant transcripts from conversations. Perfect for indie hackers exploring real-time detection via wearables or glassflow studio-style vision tools.

Verdict

At 46 stars and 1.0% credibility, GlassFlow is immature with no tests visible, but polished quickstarts and troubleshooting docs make it dead simple to prototype. Grab it for glasses hacks if you're patient with early bugs—skip for production. (187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.