Other Voice Model (Text-To-Speech, Neural Network based)

Very good

Wow, I was very impressed seeing that... I hope to see content in near future from some talented creators using this. That would gain another level of reality in VaM. Thanks for bringing this one to our crowd.

works good to me , need to do alot of time tho till the speech goes smother . but over all great work .
can be nice to have male voice too ... just sayn ...

Didn't work for me. Get this error during this step:
Run the app
Go to "Synthesis"
Click on Submit


OOPS! AN ERROR OCCURED
Please share the following error in an issue at https://github.com/BenAAndrew/Voice-Cloning-App

Type: PermissionError
Text: [Errno 13] Permission denied: 'C:\\Users\\...\\Desktop\\data\\models\\VAM Voice Model\\VAM Voice Model'
Full: Traceback (most recent call last): File "flask\app.py", line 1950, in full_dispatch_request File "flask\app.py", line 1936, in dispatch_request File "application\views.py", line 291, in synthesis_setup_post File "synthesis\synthesize.py", line 45, in load_model File "torch\serialization.py", line 594, in load with _open_file_like(f, 'rb') as opened_file: File "torch\serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "torch\serialization.py", line 211, in __init__ super(_open_file, self).__init__(open(name, mode)) PermissionError: [Errno 13] Permission denied: 'C:\\Users\\...\\Desktop\\data\\models\\VAM Voice Model\\VAM Voice Model'

I get this error
[6420] WARNING: file already exists but should not: C:\Users\###\AppData\Local\Temp\_MEI64202\torch\_C.cp36-win_amd64.pyd
but then nothing happens nothing opens just nothing.

Finally, someone with a bit of sense to make a tutorial easy to understand and follow. I tripped up on the "start the app" step, not realizing I'm supposed to "run the exe from before" and definitely didn't expect the thing to run in my browser. But I'm a dummy.
And even a dummy like me managed to get this working. THAT'S how good this person's tutorial is!
Also, thanks for this wonderful feature ^^

This is a game changer. The free online TTS are limiting and I can't afford the subscription ones. Now I can create dialog to my heart's content. Thank you!

Love the idea, I currently use several tts engines now to voice my scenes. but will defiantly give this a try too. always open to new stuff.

Fantastic. I got it set up and working in 3 minutes. It will take some time to get lines to sound the way I want them to. I would be very interested to see it refined further!

Thanks for the great guide! I've got an Nvidia 3090, I'm gonna take a crack at the scrappy little nobody :-)

Thanks for the clear instructions - this was easier to set up than I thought it would be. And thanks for the work training the model! Next step is to get these lines set up in VAM with some triggers!

is there a way to pick different voices?

I get this error trying to open the app the first time:
[6420] WARNING: file already exists but should not: C:\Users\###\AppData\Local\Temp\_MEI64202\torch\_C.cp36-win_amd64.pyd

Very great thing. This is a great idea and opens up many new doors. Please stay tuned. Especially when it is very important to you!

Amazing!

Holy guacamoley

Impressive work, this is something very much needed in VAM.

This is amazing!