Upload an Audio Recording vs. Live Transcription ?
in progress
E
Ethan Rosch
A workaround for lower CPU processing would be a way to simply record the audio, and then have the processing occur post meeting. Right now it is a live transcription; which I do not think is necessary in many cases. I think it would work well to allow me my full CPU power for the meeting, then run the transcription in the background post meeting and get my notes after some time.
E
Ethan Rosch
Amazing. Thank you
Nutshell
Ethan Rosch v1.0.7 is being pushed tonight with this feature update. It's currently building the production build and going through our validation pipeline. It'll be out in the next hour or so
Feel free to leave comments here on the feedback for it! I do plan on touching up on it over the holiday weekend so let me know!
Nutshell
Just to provide an update. We're really close to finishing up the post transcription flow. We're expecting the delivery of this within v1.0.7 on Wednesday (11/27)
I've provided some screenshot of the flow below
Nutshell
ECD: latest by 11/27
Nutshell
in progress
Starting this work today (11/20)
Nutshell
planned
Nutshell
We're planning to give users option before they start a meeting to either transcribe live or as a post processing. We'll keep you posted on when this comes out. This will definitely provide more flexibility for users.
E
Ethan Rosch
Nutshell much appreciated. Will check in the morning. best
E
Ethan Rosch
Nutshell ok - did a recording for pots transcription.
- It did record the entire conversaiton
- It did transcribe the conversation (but still not picking out individual speakers)
- in the list it showed as "not started" so I clicked some buttons and now have lost the transcription. (I think clicking the "green run arrow again hoping to start the process over)
Is there a way to extract the audio? I'd like to run a generic AI on the audio file.
Will test again.
Thank you
Nutshell
Ethan Rosch Hey Ethan, So I just spent a majority of the day trying to reproduce your issue. There was a race condition that wasn't caught. I'm pushing up the fix now. Let me know if you have any issues with the latest version of 1.0.8, sorry for the inconvenience.
Nutshell
> Is there a way to extract the audio? I'd like to run a generic AI on the audio file.
I'll have this done by next week. I know others have requested it as well.
> It did transcribe the conversation (but still not picking out individual speakers)
While Nutshell does transcribe the conversation, it doesn’t currently identify individual speakers by default due to performance considerations. At this time, speaker differentiation is achieved only by separating audio based on the microphone and speaker being used.
E
Ethan Rosch
Nutshell I'll check this again. I think Audio export is a great backup solution - as if there is an issue, then the conversation can be recovered and processed. Thank you