Guides Free neural text to speech with emotion!

[Bob Nothing]

Bob Nothing submitted a new resource:

Free neural text to speech with emotion! - Lifelike text to speech, including emotions, all for free using Azure Speech Services!

Don't you wish VAM had more story based content? I think the major thing holding this back is the lack of voice. Are you sick of using speech bubbles in VAM? Don't you wish there was an easy way to generate excellent TTS (text to speech) that sounded decent and even included emotions? Even better, don't you wish you could do it for free? Well, you're in luck!

Microsoft Azure has amazing AI neural speech text to speech, and if you use their Free tier, you can do 500,000 characters per...

Read more about this resource...

 

[EMPIR]

Is it only me or hyper link
Voice Gallery (microsoft.com)
shows this error " The page you requested cannot be found. "

 

[Bob Nothing]

Is it only me or hyper link
Voice Gallery (microsoft.com)
shows this error " The page you requested cannot be found. "

So, this link appears to point directly to the portal associated with my Azure account I setup. It appears you have to have an Azure account setup to access that portal. Without an Azure account you just get this page - https://speech.microsoft.com/portal

 

[Bob Nothing]

Is it only me or hyper link
Voice Gallery (microsoft.com)
shows this error " The page you requested cannot be found. "

Hi MerGe, I've updated the document to help you properly add the speech service to your Azure subscription.

 

[ZRSX]

Very nice guide! I had look for text-to-speech generators before; it was not that good and wasn't very good conveying emotions. This looks better, thanks for sharing

I have a sample video I made using the above script, but it's close to 700MB (4k) and I'm not sure how to upload it to share on the hub... So, if you want to point me in the right direction, I'll get it up.

VAM Hub has an upload limit of 500 MB. So you'll have to host your video separately, for instance using a MEGA link.

 

[Bob Nothing]

Very nice guide! I had look for text-to-speech generators before; it was not that good and wasn't very good conveying emotions. This looks better, thanks for sharing


VAM Hub has an upload limit of 500 MB. So you'll have to host your video separately, for instance using a MEGA link.

I've seen lots of people post videos with an embed link/player that isn't YouTube. Any idea what service it is they are using? No one seems to want to tell me, I've asked many times

 

[Bob Nothing]

Very nice guide! I had look for text-to-speech generators before; it was not that good and wasn't very good conveying emotions. This looks better, thanks for sharing


VAM Hub has an upload limit of 500 MB. So you'll have to host your video separately, for instance using a MEGA link.

Ahh I see you just posted a resource with a video clip using Redgifs. I didn't realize that would let you do audio as well. I'll give that shot!

 

[Bob Nothing]

Bob Nothing updated Free neural text to speech with emotion! with a new update entry:

Added video

I've updated this guide with a 1 minute long video of a VAM character doing the Azure AI generated audio clips.

Read the rest of this update entry...

 

[Dusk84]

Hey, just found out that not all regions are supported, you have to select one of these:
Australia East, Brazil South, West US, West US 2, West Europe, North Europe, Southeast Asia, East Asia, West Central US, South Central US, East US, East US 2, Canada Central, Japan East, Central India, UK South, Japan West, Korea Central, France Central, North Central US, Central US, Central US EUAP

 

[Jocks3D]

So how do you use this to make VaM models talk? (Sorry if I missed this info somewhere.)

 

[Bob Nothing]

So how do you use this to make VaM models talk? (Sorry if I missed this info somewhere.)

You use the 'head audio' property of a person atom. So, if you're using VAMs built in animation triggers, you would select the audio files you want in the scene, then on the trigger select the person atom, then the 'head audio' option, then 'play now' and select the audio file in question. RT Lip sync plugin adds a lot of realism to the actual mouth movement while talking.

 

[Bob Nothing]

Just an update for everyone, MS has added a lot more additional voices with emotions.