AllTalk TTS

[SensualTiffany]

Did you do this online or did you load the model in your computer?  

As the thread title suggests - locally installed AllTalk TTS v2 and locally trained Nikki's voice.

PM me the script and I’ll work on it.

It's the second one in this post: https://www.likera.com/forum/mybb/Thread...2#pid79132

So, I didn't spend a huge amount of time and it took a bit of tweaking, but here is the beginning of your text, generated from the T5-TTS.  I added the Theta because there were interestingly different silences, created by the TTS.  I like Theta or Background music myself.

Likera-Experiment-Edited.mp3 (Size: 440.36 KB )



Couldn't help myself:  Here is a version with some...added sound.

Likera-Experiment-WithMoans.mp3 (Size: 717.91 KB )



Cheers.

[Like Ra]

So, I didn't spend a huge amount of time and it took a bit of tweaking, but here is the beginning of your text, generated from the T5-TTS. 

Is it related to AllTalk TTS? Or is it a different one? If a different, let's move it to a separate thread.

[SensualTiffany]

So, I didn't spend a huge amount of time and it took a bit of tweaking, but here is the beginning of your text, generated from the T5-TTS. 

Is it related to AllTalk TTS? Or is it a different one? If a different, let's move it to a separate thread.

Apologies.

Yes, it's a different program.  F5-TTS.  Here is a link to their webpage LINK

They have an online version that seemed to crash a lot. 
I installed the local version on my computer and that is what I am using.

We should start a new thread for sure.

Again, apologies.

Tiffany.

[Like Ra]

I installed the local version on my computer and that is what I am using.

How did you do that? It's not mentioned on their website.

Yes, it's a different program.  F5-TTS. 

Were all the files generated by the local program?

[Like Ra]

Actually... F5 TTS is supported from within AllTalk TTS, so both threads can be merged again 😁

[SensualTiffany]

Actually... F5 TTS is supported from within AllTalk TTS, so both threads can be merged again 😁

Please do.

Playing around some more with my TTS model, I used Isabella Valentines voice.  I'll post my raw, unedited Mantra Script, voiced by Isabella Valentine.  It needs a lot of spacing between words to get the pacing right and some fixes for the mispronunciations, but it shows some decent accuracy for the 15s clip of Isabella that I fed it.  

Enjoy:  
Sensual_Tiffany-Isabella_Mantra-RAW-Unedited.mp3 (Size: 2.76 MB )

[Like Ra]

Playing around some more with my TTS model, I used Isabella Valentines voice. 

How do you clone voices? Using AllTalk?

[SensualTiffany]

Playing around some more with my TTS model, I used Isabella Valentines voice. 

How do you clone voices? Using AllTalk?

I'm using F5-TTS

You said earlier, "Actually... F5 TTS is supported from within AllTalk TTS, so both threads can be merged again 😁" so I put it here again.

[Like Ra]

I'm using F5-TTS

OK, how do you use it?

F5 TTS is supported from within AllTalk TTS

Yes, F5 TTS engine is included in AllTalk, but only TTS, the voice cloning is not supported.

[SensualTiffany]

I'm using F5-TTS

OK, how do you use it?

F5 TTS is supported from within AllTalk TTS

Yes, F5 TTS engine is included in AllTalk, but only TTS, the voice cloning is not supported.

Then maybe we should move this to the other as well.