• Hi Guest!

    We are extremely excited to announce the release of our first Beta1.1 and the first release of our Public AddonKit!
    To participate in the Beta, a subscription to the Entertainer or Creator Tier is required. For access to the Public AddonKit you must be a Creator tier member. Once subscribed, download instructions can be found here.

    Click here for information and guides regarding the VaM2 beta. Join our Discord server for more announcements and community discussion about VaM2.
  • Hi Guest!

    VaM2 Resource Categories have now been added to the Hub! For information on posting VaM2 resources and details about VaM2 related changes to our Community Forums, please see our official announcement here.

Anyone tried Voice.AI to create your own voice clips, in other's voices? M2F, or F2F, or whatever you like.

AWWalker

Another White Walker (AWWalker)
Featured Contributor
Joined
Jun 1, 2020
Messages
435
Reactions
2,878
I tried it out, it seemed pretty cool, and if we could with good lip syncing you can breathe even more life in to your characters in animations. Working on one now, to see how real i can get it to look/sound.

Voice AI Home

It's a Real-Time AI Voice Changer and could breath life in to scenes, with a little practice. I've gotten a quite a few good results with my shitty voice, with Emma Watson as the speaker. Almost sounds like her, but for scenes, if you just want a girl voice, and can talk like it, or are a girl, and want to change your voice, check it out.

If you want to try it out. It's free, uses some compute to help train new voices. Interested, check it out. I'm been doing a scene to see how it goes. Kinda cool if you don't want some generic text to speech sounding scenes. Use Audacity (or something similar) to remove the 2 second blip at the end, and if your mic is meh, it'll also remove crackling and static.
 
I tried it out, it seemed pretty cool, and if we could with good lip syncing you can breathe even more life in to your characters in animations. Working on one now, to see how real i can get it to look/sound.

Voice AI Home

It's a Real-Time AI Voice Changer and could breath life in to scenes, with a little practice. I've gotten a quite a few good results with my shitty voice, with Emma Watson as the speaker. Almost sounds like her, but for scenes, if you just want a girl voice, and can talk like it, or are a girl, and want to change your voice, check it out.

If you want to try it out. It's free, uses some compute to help train new voices. Interested, check it out. I'm been doing a scene to see how it goes. Kinda cool if you don't want some generic text to speech sounding scenes. Use Audacity (or something similar) to remove the 2 second blip at the end, and if your mic is meh, it'll also remove crackling and static.
It's possible to make anyone say whatever you want. For example, find a video where Emma Watson speaks on YouTube, ideally as clearly as possible and then clone her voice. Check out: https://beta.elevenlabs.io/

Have fun! ;)
 
Yes, Emma watson i downloaded her voice, it is the same pitch and roll, bu;t you have to get her accent down to make it believable.
 
It's possible to make anyone say whatever you want. For example, find a video where Emma Watson speaks on YouTube, ideally as clearly as possible and then clone her voice. Check out: https://beta.elevenlabs.io/

Have fun! ;)
Yes, Emma i downloaded her voice, it is the same pitch and roll, bu;t you have to get her accent down to make it believable. Just watch a bunch of the later harry potters lol.
1683349943976.png
 

This is meant more for vocals but a lot of the voice models work with the "speech" mode. Tons of famous ones but also random males and females. The voice input you give it should be clear, well articulated, and without background noise if possible. You can use anything really. But I just record myself speaking in audacity then uploaded the whole string of phrases/words. Then I manually split it once its in their voice. Play with the pitch setting if it's not sounding right.

There is a text to speech version with probably more voices, but depending on the voice model you probably won't have any expression. That's why I go the voice to voice route.
 
Back
Top Bottom