AllTalk TTS

[Like Ra]

Reinstalled. Started relatively "small". And ... it works!!! And the result is amazing!
Testing further ...

[Like Ra]

Ah... good old times of neural network trainings 😅

Well, I just had to do a little work.

Here is TTS Nikki with a short, barely edited 4 minute clip of a section of script.
Enjoy.

Beginning are a series of just WORDS or PHRASES until the file starts talking about Pink Mist. 

The program uses only a 15min sample and creates the TTS from it.  I played around with several base samples, so the difference in tones.

I’ll keep playing with it, but the initial plan is to modify one of my favorite Nikki files.  All those disturbing “Boy” references will be more feminine friendly.

Damn gurl, you are spirit talker, with such skills you can bring back the classics or even more.
Amzing werk, intonation and sound is quite well.
For 5 min test run, it is outstanding A+

Can you try Madame Y robotic voice for sake of testing ? on the other hand, nevermind.
You aeady did "magic", I suppose if AI can do Nikki, Madame Y is weak candidate to challange the system.

Your wish is my command:  A little Madame Y.
Had to strip out music first, but I think it might be passable when mixed with a binaural and some decent music.
Thoughts?

Plain:
  MadameY-Helga.mp3 (Size: 96.26 KB / Downloads: 27)

With Theta: 
  MadameY-Helga-Theta.mp3 (Size: 141.13 KB / Downloads: 26)

With Music:  
  MadameY-Helga-Music.mp3 (Size: 385.48 KB / Downloads: 24)

[Like Ra]

A little Madame Y.

Excellent! The "style" is recognizable!
With some more data and a bit more training, the "metal" should disappear.

Had to strip out music first,

How did you do this?

A little Madame Y.

Excellent! The "style" is recognizable!
With some more data and a bit more training, the "metal" should disappear.

Had to strip out music first,

How did you do this?

I used a free online tool 
Vocal Remover

But am looking for a better one. Reference audio needs to be as clean as possible for the F5.  I can “dirty” it back up in Audacity.

Helga is good girl, Tyfanny

[Like Ra]

OK... here comes the learning curve ... And bugs ... bugs ... bugs ...

The TTS skips, changes text, and sometimes refuses to generate anything.

Anyway, here's some results:


  nikki2_17405326384b6e6.mp3 (Size: 1.25 MB / Downloads: 32)

OK... here comes the learning curve ... And bugs ... bugs ... bugs ...

The TTS skips, changes text, and sometimes refuses to generate anything.

Anyway, here's some results:

Did you do this online or did you load the model in your computer?  PM me the script and I’ll work on it.

[Like Ra]

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

[Like Ra]

Trained a new test Nikki's voice - 7min is perfectly enough. Amazing...

But.... The TTS skips even on the "standard" voices. Is AllTalk TTS based on too old dependencies?