unreliable recording and speaker diarization

[kodjima33]

UPDATED DIRECTION

Llet's implement saving voices, so that once the user has labeled a speaker (or it was auto-labeled), we saved it to speaker library and it would be reused and auto-labeled in future conversations

It will help us to properly name conversations later and automatically share them

Existing "saved voices" library is located on "identifying others" page

I've also attached an example screenshot of how imitless does it, but i don't think we need to change a UI for this feature

---

I talked to 7 omi users (mobile) and top-1 issue heard was poor quality of diarization (speaker assignment) and reliability.

As Im writing this, i just had a conversation with someone for 20 minutes but only 2 !!!!!!!!!!!!!!! minutes were captured. In that conversation i was the only one who was speaking but our app didn't even assign my name

• Check why omi didn't capture 80% of this conversation - make sure I understand the problem and then fix it
• suggest Nik a solution for speaker diarization to make it THE BEST IN THE DAMN WORLD, don't be lazy even if you need to invent smth new

[kodjima33]

do this today pls @beastoin

[beastoin]

omi didn't capture 80% of this conversation

you used omi mac os right ?

[beastoin]

7 omi users (mobile) and top-1 issue heard was poor quality of diarization (speaker assignment) and reliability

i need all contacts so i can talk to them, especially i need their uid to check the data.

[kodjima33]

@beastoin device

[beastoin]

give me the app version and the firmware version, please

[kodjima33]

@beastoin 1.0.78 471

12 firmware

[M-SRIKAR-VARDHAN]

Hey , I've been digging into the "poor diarization" and "missing audio" issues (re: Issue #2806). I believe the current reliability issues stem from two linked problems in the pipeline, and I'd like to propose a fix I'm working on:

1. The Root Cause of "Missing Audio" (VAD Gating)
The current VAD/Silence thresholds (likely default Silero >0.5) are too aggressive for wearable audio, which often has varying distance-to-mic. This causes the system to treat "quiet" valid speech (like a friend across the table) as silence, dropping ~80% of some conversations.

• Fix: Decouple VAD from the recording trigger. Implement a "soft" VAD with a lower threshold (0.3) and increased speech_pad_ms (500ms+) to capture the full context, not just loud peaks.

2. State-of-the-Art Diarization (Pyannote)
Deepgram's streaming diarization struggles with single-channel wearable audio.

• Fix: Switch to a Global Clustering approach using pyannote-audio. Instead of diarizing chunk-by-chunk (which forgets context), we generate embeddings for the whole session and cluster them. This fixes the "Speaker 0 / Speaker 1" flip-flopping.

3. "Granola-Tier" Smart Titles
To solve the generic "Conversation #24" titles, I propose a post-processing step:

• Pass the first 120s of the diarized transcript to the LLM with a specific prompt: "Extract distinct speaker names and rename this file 'Meeting with NAME'."