Genesys Cloud - Main

 View Only

Discussion Thread View
  • 1.  Amazon Polly Voice Branding

    Posted 05-24-2022 10:00
    Hi All, 
         I have a system running Amazon Polly and it works out of the box.
    I'm wondering if anyone has tried to customize the voice using features explained in this article?
            Amazon Polly Features
    Amazon Web Services, Inc. remove preview
    Amazon Polly Features
    Amazon Polly provides an API that enables you to quickly integrate speech synthesis into your application. You simply send the text you want converted into speech to the Amazon Polly API, and Amazon Polly immediately returns the audio stream to your application so your application can begin streaming it directly or store it in a standard audio file format, such as MP3.
    View this on Amazon Web Services, Inc. >

    #Integrations
    #SystemAdministration
    #Telephony

    ------------------------------
    Chris Martin
    CCS Medical
    ------------------------------


  • 2.  RE: Amazon Polly Voice Branding

    Posted 06-03-2022 08:07
    Hi Chris,

    I do record prompts with Amazon Polly and sometimes have to customize the audio with SSML to make it sound more natural.

    The integration with GC also works very well and you can use neural TTS with it.


  • 3.  RE: Amazon Polly Voice Branding

    Posted 06-07-2022 08:55
    We use Amazon Polly on our end. We create recordings (with SSML alterations) for prompts that are static, but use Amazon Polly on-the-fly for any variables. Our Play Audio segments are constantly flipping between pre-recorded prompts and real time variables, which is seamless to the customer. 
    Genesys has some nice functions that you can wrap around the returned variables (date, currency, etc) in order to make things sound more natural. Our experience with Amazon Polly has been overwhelmingly positive.

    ------------------------------
    Cory King
    IT Lead
    IGS Energy
    ------------------------------



  • 4.  RE: Amazon Polly Voice Branding

    Posted 06-07-2022 09:07
    Edited by Chris Martin 06-07-2022 09:07
    Hey Cory, thanks for the info.
    Do you have a smooth way to generate a prompt using the polly TTS so the CX is consistent?
    Hopefully something better than taking the recording and cutting it down.

    Thanks,
      Chris

    ------------------------------
    Chris Martin
    CCS Medical
    ------------------------------



  • 5.  RE: Amazon Polly Voice Branding

    Posted 06-07-2022 09:48
    Hi Chris - 
    We download the recording from the Polly section AWS interface as an MP3, then use Audacity to convert it to a WAV and then upload into Genesys; I believe you would have had to create an AWS account when setting up the Polly integration. Once you do it a couple of times, it's a pretty straight-forward process. The Genesys and Amazon Polly integration is tight enough that flipping between pre-recorded audio and on-the-fly playback of variables is a really good customer experience. 

    Let me know if I can offer any additional advice!

    ------------------------------
    Cory King
    IT Lead
    IGS Energy
    ------------------------------



Need Help finding something?

Check out the Genesys Knowledge Network - your all-in-one access point for Genesys resources