Who said that? Voice Recognition
complete
S
Sean Savatt
Add post-meeting voice attribution that allows users to tag speakers by name and role, then automatically recognize those voices in future meetings. With saved background and org context (pro feature)(titles, reporting relationships, frequent collaborators), Hedy AI could generate summaries, action items, and follow-ups with names already attached and better prioritization. This would move Hedy beyond transcription into true meeting intelligence by understanding who is speaking and how their role impacts decisions and next steps.
Julian Pscheid
updated the status to
complete
Over the last few releases, we've been building up to having solid speaker identification and separation in the transcript. If you haven't tried it yet, switch to the Nemotron speech recognition model in your settings. We do think we have this pretty well covered at this point.
The one thing that still is outstanding for the future is to carry over the speaker identities between sessions and build a topic specific knowledge base per speaker. That's on our radar to add down the road.
L
Lucho
Julian Pscheid About Knowledge Base per speaker, maybe merging the concept of WBS + Speaker profile role in a topic/project.
Julian Pscheid
Just a quick note that the Nemotron speech recognition model rolling out in 3.5.0 has speaker separation built in. At this time this model is only available on iOS and macOS, but we plan on adding it for Android and Windows as soon as it's possible. If you are on iOS or macOS, I highly recommend switching to Nemotron!
J
Jason
Julian Pscheid Yes! Very excited for this update!
Jonathan Tepper
Julian Pscheid Look forward to Windows 11 speech recognition model! And when Hedy has carry over the speaker identities between sessions and build a topic specific knowledge base per speaker, that will be AMAZING!
Julian Pscheid
Jonathan Tepper Hi Jonathan, Nemotron speaker recognition is already available in Windows, and I recommend you try it out! Just make sure to update to the latest version first.
Jonathan Tepper
Julian Pscheid Confirmed! I do have it set up that way, I just realized the speaker's are listed clearly in the app. I was looking on the web interface of Hedy and I only saw speakers one and two etc. I will make sure that I refer to the hedy app for now. Is this a known feature to work only in the app? Thanks much for your quick response!
Julian Pscheid
Jonathan Tepper Speakers should now also show in the web app!
Jonathan Tepper
This would be a game changer. Even if it was with accuracy a Voice 1, Voice 2, Voice 3, etc. then the user could identify names afterwar, it would make the coaching, negotiating, and other options so much more powerful.
R
Rudy
After using Hedy for several months, I’ve realized that speaker identification is the most critical feature the platform needs. Almost every issue I encounter with transcriptions, summaries, and action items stems from the AI misattributing who said what. Because it can't distinguish between speakers, it makes wrong assumptions about task ownership and meeting tone, often providing incorrect answers when I ask questions about a session.
Orian Sandstein
yes yes yes yes yes indeed +1