Hi - a very informative video thanks - now I was wondering would it be possible with azure / power automate to trigger when an audio file is saved to a OneDrive folder to transfer that to text and then summarise using ai before saving as a word doc in another folder?
Hi @andrewsmith-bz1lf, yes this could be possible with onedrive and power automate, as well as azure blob storage and a logicApp that would be triggered when a file is created in the blob storage. let me know if you tried it already?
Is an understanding of Ubuntu or programming required in order to use Azure speaker recognition? I would like to use is there a speaker recognition, but there is no user interface that I can find that allows me to upload audio files and assign names to voices
Hi David, I used Ubuntu because this is what i know, however you can accomplish the same using powershell. for automation typically scripts and functions are the way to go. were you able to do what you were trying to do? btw thanks for watching
![Felix "Unfair" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/Oswujxm2Ag0/mqdefault.jpg)
Great tutorial, it worked for me. now you have one subscriber more.
Glad to hear/read! thank you
Hi - a very informative video thanks - now I was wondering would it be possible with azure / power automate to trigger when an audio file is saved to a OneDrive folder to transfer that to text and then summarise using ai before saving as a word doc in another folder?
Hi @andrewsmith-bz1lf, yes this could be possible with onedrive and power automate, as well as azure blob storage and a logicApp that would be triggered when a file is created in the blob storage. let me know if you tried it already?
@@freddydubon4619 This is exactly what I need to do and I'm having a hard time figuring out how to implement it.
Is an understanding of Ubuntu or programming required in order to use Azure speaker recognition? I would like to use is there a speaker recognition, but there is no user interface that I can find that allows me to upload audio files and assign names to voices
Hi David, I used Ubuntu because this is what i know, however you can accomplish the same using powershell. for automation typically scripts and functions are the way to go. were you able to do what you were trying to do? btw thanks for watching
can you please help it does not tell about the speaker 1 and 2 and how to achieve that
Thank you for this informative video. Can you please provide inputs on how to get Transript along with the timestamps
Very helpful and easily understandable..i have a query..do we need to install python software on the VM
I am glad it was helpful, and for this demo I did install Python on the VM
Hi, Wheres the video of the serverless Solution ? Thanks Kind Regards
Great question, let me work on it.
lets say audio is in english and we want to get subtitle in spanish and other languages. Is it possible
yes that is possible, you can send the transcription to the translate service and get a transcription translated to different languages.