I'm not sure if it's just me or not, but it seems like the voice lines for the synth voice for nate doesn't work for automatron, speaking to Ada just has the original voice.
been using this for a while now and found several lines consistently not voiced. but also with other voice changers, so i guess it is just how it goes. so really only here to give ideas for playthrough's. i made a Charse Bronson 'Death Wish' character that uses the ghoul voice. and found this little mod for the synth voice: ultron prime at Fallout 4 Nexus - Mods and community (nexusmods.com) i tried making a Clubber Lang (Mr. T in Rocky III) for the supermutant voice, but it was Too Much... for me anyway. felt like a phool
anyway this mod adds a lot of potential roleplay options. you could even make Nora a She Hulk with ghoul or supemutant voice and female mutant mod.
Trying to use batch conversion. It just not work! It gives this
Traceback (most recent call last): File "server.py", line 335, in do_POST File "python\xvapitch\model.py", line 326, in infer_batch File "D:\Modding\XVASynth\.\resources\app\python\xvapitch\xvapitch_model.py", line 223, in infer_advanced return self.infer_using_vals(logger, plugin_manager, cleaned_text, text, lang_embs, speaker_embs, pace, None, None, None, None, None, None, pitch_amp=pitch_amp) File "D:\Modding\XVASynth\.\resources\app\python\xvapitch\xvapitch_model.py", line 292, in infer_using_vals x, x_emb, x_mask = self.text_encoder(input_symbols, x_lengths, lang_emb=None, stats=False, lang_emb_full=lang_emb_full) File "torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "D:\Modding\XVASynth\.\resources\app\python\xvapitch\xvapitch_model.py", line 602, in forward x = torch.cat((x_emb, lang_emb_full), dim=-1) RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 27 but got size 1 for tensor number 1 in the list.
could use some help making a voice mod i have the voice model i want loaded but when i try to drop the cvs files in the batch file, i get an error saying game id fallout 4 doesnt exist? plugin is activated delimeter is 1 whats the issue help?
Woah. I'm doing an alternate start female Ghoul explorer playthrough and I was surprised at how much the Ghoul voice immersed me! Awesome job you did with this.
Only complaints I'd have is that some voice lines sound very synthy/layered. The panting sound when sprinting is also not very sexy sounding... I know nothing about using AI to modify voices, but I hope these can get improved some time! I'm gonna give the male ghoul a shot and if that works better, I'll switch to a male Ghoul playthrough. Thank you though! : ) Endorsed!
75 comments
so really only here to give ideas for playthrough's. i made a Charse Bronson 'Death Wish' character that uses the ghoul voice. and found
this little mod for the synth voice: ultron prime at Fallout 4 Nexus - Mods and community (nexusmods.com)
i tried making a Clubber Lang (Mr. T in Rocky III) for the supermutant voice, but it was Too Much... for me anyway. felt like a phool
anyway this mod adds a lot of potential roleplay options.
you could even make Nora a She Hulk with ghoul or supemutant voice and female mutant mod.
It gives this
Traceback (most recent call last):
File "server.py", line 335, in do_POST
File "python\xvapitch\model.py", line 326, in infer_batch
File "D:\Modding\XVASynth\.\resources\app\python\xvapitch\xvapitch_model.py", line 223, in infer_advanced
return self.infer_using_vals(logger, plugin_manager, cleaned_text, text, lang_embs, speaker_embs, pace, None, None, None, None, None, None, pitch_amp=pitch_amp)
File "D:\Modding\XVASynth\.\resources\app\python\xvapitch\xvapitch_model.py", line 292, in infer_using_vals
x, x_emb, x_mask = self.text_encoder(input_symbols, x_lengths, lang_emb=None, stats=False, lang_emb_full=lang_emb_full)
File "torch\nn\modules\module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "D:\Modding\XVASynth\.\resources\app\python\xvapitch\xvapitch_model.py", line 602, in forward
x = torch.cat((x_emb, lang_emb_full), dim=-1)
RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 27 but got size 1 for tensor number 1 in the list.
Only complaints I'd have is that some voice lines sound very synthy/layered. The panting sound when sprinting is also not very sexy sounding... I know nothing about using AI to modify voices, but I hope these can get improved some time! I'm gonna give the male ghoul a shot and if that works better, I'll switch to a male Ghoul playthrough. Thank you though! : ) Endorsed!