Sexlab Survival

[Monoman1]

I've got to say. It seems like the more articulate the voice type the better it works out. Mumbly nord + weird accent has issues.

 

Surprisingly long, snooty high elf comments work out pretty well IMO. Conversely, probably wouldn't be very good at expressing lust/anguish etc. 

Get away from me. You stink of sperm.wav

 

My dog will be happy to see you!. Why don't you get down on all fours and I'll go get him..wav

 

Oh Look! It's the girl that likes to suck big horse cocks. The bigger the better. Right, sweetie.wav

 

Well well. If it isn't the town whhore!., Shouldn't you be on your back somewhere.wav

 

Still takes a pretty long time fiddling around with wording and punctuation but definitely nowhere near the old fashioned way. 

Edit: LL must be doing some compression. Sounds a lot more crackly when played back here than locally. 

 

3 hours ago, Lupine00 said:

It is, and ... it already has ... and the high quality deepfakes are already demonstrating it.

I'd say there's about 3 people on this forum that understood this post. 

Sadly I'm not one of them. But if it helps bring more accurate voice lines I'm all for it. 

 

[sattyre]

18 minutes ago, Monoman1 said:

I'd say there's about 3 people on this forum that understood this post. 

Sadly I'm not one of them. But if it helps bring more accurate voice lines I'm all for it. 

 

LOL.  yup, and I'm not one either, but it certainly makes Lupine sound like a smarty pants, considering she's one of those three.

 

Good on ya, it goes to show we come from all walks of life, all devious quirks aside.

[Monoman1]

Player informationals:

 

Ugh, I'm soaked in cum.wavMy pussy is dripping wet.wavI've got to get milked soon, or my tits might just, pop!.wavGod damned stupid armbinder!.wavI'm so horrny right now Id fuck anyone!.wav

[Bondage Queen Slaveia]

If you're looking for feedback, those voice lines are awesome in my book! I'd love having those in the game! Especially armbinder and bondage ones - I feel like those kinds of comments are the most underrepresented, and would add a lot to the immersion.

Also, your right, it's funny how good the high elf female sounds.

[Lupine00]

7 hours ago, Monoman1 said:

I've got to say. It seems like the more articulate the voice type the better it works out. Mumbly nord + weird accent has issues.

That's probably because the articulate speech is a closer match to the LJSpeech dataset used to train the Tacotron2 model that feeds into the FastPitch model generation.

Also male speech is just harder because it's made of mumbles, contractions, dropped syllables, and grunts.

Spoiler

It's well known that at puberty, the testosterone overdose paralyses the speech centers and renders the male child unable to voice words clearly, and instead they are reduced to grunts and the occasional "ah'yup". Some relearn to speak after this incident, others do not.

 

The sound on Monoman's latest samples is not robotic, but the pacing is odd, and they're still a bit like the cut+paste lines he's made simply by editing.

Maybe, it's possible to overcome things like the fast falling tone on "god damned" so it has the appropriate emphasis on the curse, but ... takes a lot of experimenting and pain I imagine?

 

The high-elf ones are very good, though emphasis goes on the wrong word now and again the words themselves sound correct, even down to the accent.

 

 

On the topic of the lines we have in SLS right now...

 

It seems like we have almost everyone saying everything, and though the lines are great in some contexts, they land badly in others.

For example, just about everyone is telling me to get lost! Well... That's fine for ... almost no NPCs ... as most NPCs have some kind of interaction they will eagerly perform and it transitions badly.

 

e.g.

 

Belethor: "Get lost."

Player invokes dialogs.

Belethor: "How can I help you?"

Player: "Wow! That's some attitude change!"

 

Or it comes off even stranger with things like the golden claw quest.

 

Vendors and unique NPCs should probably not be so eager to dismiss the PC, insult her, or otherwise emit random abuse, as it's likely that their main dialogs will then say something completely contradictory. Nazeem is an obvious exception of course, though the ability to insult him back is sorely lacking.

 

Sometimes less is more, and all that.

 

 

In terms of informational messages, basic stuff like tiredness, hunger and thirst would be useful too, even though EatSleepDrink has a tremendous tummy rumble.

[firepunch1]

19 hours ago, Monoman1 said:

Can not for the life of me get serana to say 'tits'. Keeps saying 'its'. Which is odd. I would have thought serana would have a mountain of dialogue to sample from. 

https://vocaroo.com/14iaxsy7TzBT 

It would seem what the words you choose to put around the given word has a pretty large effect on how it'll be pronounced as well, I'd say this sounds like "tits", and the only thing he changed was the words leading up to it (i.e. no spelling magic or punctuation.)

 

Input he used:

 

 

[Monoman1]

1 hour ago, firepunch1 said:

Input he used:

Haha. That's brilliant. But how the hell did they come up with that

2 hours ago, Lupine00 said:

they land badly in others.

In fairness, LL mods have always had that problem. Skyrim itself has it as well. It'd be nice if say the companions were all snotty in the beginning to a new whelp and later eased back but achieving that sort of granularity is difficult and time consuming. And just probably not really worth the effort. 

[Lupine00]

1 hour ago, Monoman1 said:

And just probably not really worth the effort. 

 

In an ideal world, vendors would have their own sleazy dialogs that were vendor appropriate.

There are opportunities for bonus comedy.

In contrast, the "Get lost" dialog works in almost no situation at all.

 

It would work nicely for a dedicated prostitution mod, in the result of a failed solicitation attempt, but ironically, no such mod has any audio lines at all.

 

Spoiler

"Get lost" has some very specific issues.

 

Unlike most of the dialog in SLS, which is background incidental. "I bet you have a nice body under those clothes."

Well... maybe I do, assuming I'm wearing clothes, which ... I'm not ... but it doesn't matter because there's no implied consequence.

The only implied consequence for such a line is further dialog with Hulda (or whoever, which we know doesn't exist).

 

But "Get lost" is doing something different. It implies an escalation if you don't comply.

But there is no escalation, nor even an expectation of compliance.

Neither dialog nor behavior will fit, except in that narrow case I noted above, where you're soliciting, and fail. If, by chance you were to get the line then, it would make sense, but the odds of that are slim to none.

 

 

What's worth the effort is, of course, a matter of personal perspective. But the impact of a dialog - any dialog - is proportional to its appropriateness.

 

Sure, there are many weak spots in Skyrim's vanilla dialogs, but that's what dialog mods were invented to address, not perpetuate.

[Monoman1]

I didn't realize this but you can sort of manipulate the inflection by grabbing the blue bars and raise/lower them. The effect is pretty extreme so small adjustments are best but it's useful. I'm also having better luck breaking sentences up rather than using longer ones. Long sentences can become weirdly garbled (sometimes).

 

Yes! That's it. Pound my ass!.wav

 

Just look at that lovely fat cock. I'd love to suck it dry. But I'd better not.wav

 

Hold it there pumpkin.wav

 

Thats it baybee! Shake that ass!.wav

[Lupine00]

50 minutes ago, Monoman1 said:

you can sort of manipulate the inflection by grabbing the blue bars and raise/lower them

The up-down arrow is a clue?

 

You can also adjust the length of each letter, though the interface for it is slightly less obvious; it works on the last letter you edited.

 

I found that just putting in a comma makes a big difference.

You can put commas around a word to split it out.

 

Also, you can replicate a letter and then adjust the length and tone of the different copies, to create a rise or fall.

Putting an apostrophe can also have an effect. I think it's like a space but shorter.

 

Try "Yewer ful of sh'it" vs "Yewer full of, shit", for example.

 

Sometimes it seems better not to double letters you would spell doubled.

Sometimes it seems better to roll words together phonetically.

The Serana model is just bad. I suspect there was a problem with a lack of sufficient training data for the FastPitch there.

Might be able to get some good results by making models for the voice replacers that exist.

Exclamation mark works too, but it's a bit iffy in some models.

e.g. "You, arr, full, of. Shit!" in FemaleCondescending; the full stop allows the "shit" to begin with the correct emphasis.

Sometimes swapping a d for a t (soft for hard) is effective.

e.g. "You, ar, fullov. Shid."

 

Realistically, making voice lines with this tool is easier than recording them (which is actually hard work and requries a good recording set-up and a lot of edits).

 

I think we're looking at a new year full of old mods revoiced with actual voices, and new mods that are all about voice.

So exciting!!!

[Monoman1]

7 minutes ago, Lupine00 said:

The up-down arrow is a clue?

7 minutes ago, Lupine00 said:

You can also adjust the length of each letter, though the interface for it is slightly less obvious; it works on the last letter you edited.

Yep. Just figured that out too. Pretty good program I have to say. I'm impressed. Though there are some bugs and the UI could be a little better. You know what mod could really use this? SLSF. 

[Lupine00]

46 minutes ago, Monoman1 said:

You know what mod could really use this? SLSF. 

Or sexist guards?

 

"...to suck it dry, but I better not..."

That came out perfect. Just perfect. So whistful.

But why not? Why not???

 

CUDA device not working for me in this though ... perhaps a path or version issue?

Will investigate another day.

 

Oh, just noticed it's all service driven. You can write your own client to post direct to the service. The input is very simple.

Using that approach you can automate re-processing all your lines whenever models are updated or whatever, or just try a dozen combinations and run them all at once for review later. Look in server.log to see what I mean.

[Monoman1]

36 minutes ago, Lupine00 said:

Or sexist guards?

True. Loads of possibilities. It's still tons of work though. 

1 hour ago, Lupine00 said:

I think we're looking at a new year full of old mods revoiced with actual voices, and new mods that are all about voice.

So exciting!!!

I think you're right. But you know, having worked fairly extensively on voice mods, I see (potentially) fairly major issues ahead. 

 

One is this from 'Say()' in the ck wiki: 

• If used on an actor and that actor attempts to initiate normal dialogue (for example a random greeting) while saying something through Say(), the game will crash to desktop.

 

So I think maybe what the modding community could do with now is a dialogue framework. Something that would accept topics and prioritize/play them back without everything conflicting and becoming a super garbage fire when every mod under the sun want's to push dialogue. SLS and STA sort of has this kind of system but I was never 100% happy with it. The problem is that pushing a topic from one mod to another without dependency is tough because the conditions used on the topic to limit npcs saying the lines is.... difficult. Only some conditions seem to work. I spent ages messing around with various conditions and never really got anywhere. A magic effect seems to be the best but of course you can't add a condition for that without dependency. 

 

To get around this, SLS when it wants to send a topic to STA to say it starts the quest, sends the line and stops the quest again. This is not great. There are timing issues involved. 

 

The only other thing to try maybe is an injected faction form. Not sure you can inject faction forms. I might have even tried it. Can't remember. 

 

I have to get out of these bindings, sooon.... or Ill endup as someones, ffuck toy..wav

 

Hold it there girl. You know the drill. Let me see your papers..wav

[Lupine00]

22 minutes ago, Monoman1 said:

If used on an actor and that actor attempts to initiate normal dialogue (for example a random greeting) while saying something through Say(), the game will crash to desktop.

The majority of existing mods aren't exercising that bug though.

They rely on the dialog system "as intended" and hellos.

They just need Fuz'd text upgraded with voice.

 

It's mainly STA that gets excessively chatty.

 

And yes, a dialog framework that runs all the speech through a thread-safe queue and a single thread is probably a requirement if we want to share "Say()" without crashes.

Just imagine the situation in Slaverun?!

But it's already resolved for now.

 

 

Repeating letters sometimes makes robot voice. I tried it with "sune", which also worked, but maybe not what you were after.

"I have to get out of these bindings sune. Or I'll end up as someone's fuck toy."

Then I bumped up the pitch of the 'u' in sune just a little. Sounds nervous.

I have to get out of these bindings sune. Or I'll end up as someone's fuck toy..wav

 

Trying to create anything with more than the slightest bit of emotion is near impossible though.

The data just isn't made for it.

[Durante]

I've been testing this synthesizer yesterday, had lots of good results providing the sentences aren't long and matching. I'll be honest though not all of voices are perfected even in the green list, apart from FemaleNord, most still have a robotic residue in the voice whatever the input.

 

A bit of advice: The tone of the speech, and spoken words is letter capitalization, comma, dot or exclamation mark sensitive. You might get a slightly or completely different result of quality and intonation when for example saying Hello world.... Versus Hello world or Hello world!

 

FemaleElf:Sex with you is my guilty pleasure.wav

Filthy nord, lick me clean.wav

I'm going to suck you dry.wav

Be a good doggy.wav

 

FemaleNord:Be a good doggy.wav

I will haul you into the dungeon for some private fun time.wav

 

You won't sound so tough when I break you in the dungeon.wav

 

Don't mess with me bitch.wav

 

These sound funny but still almost no robotic sound:

Don't forget who you belong to, fucktoy.wav

 

 

 

FemaleYoungEager: I am daddy's special little girl..wav

 

MaleGuard: Where's the money, Lebowski!.wav

[Monoman1]

Has anyone found that adjusting the letter length usually causes the generation to fail - 'Something went wrong'? Then you've got to change a letter etc to get it back working?

[Durante]

2 minutes ago, Monoman1 said:

Has anyone found that adjusting the letter length usually causes the generation to fail - 'Something went wrong'? Then you've got to change a letter etc to get it back working?

 

Yes, its a common bug.  In my case it crashes the generator thus having to restart.

[Monoman1]

1 hour ago, Lupine00 said:

CUDA device not working for me in this though ... perhaps a path or version issue?

Will investigate another day.

Think you need another download: https://developer.nvidia.com/cuda-10.1-download-archive-base

[Lupine00]

8 hours ago, Monoman1 said:

Has anyone found that adjusting the letter length usually causes the generation to fail - 'Something went wrong'? Then you've got to change a letter etc to get it back working?

You can see how this fails if you look in the log. It's a UI bug. The number of entries is mismatched.

Often you can change the length and it's OK. I don't find it usually causes failure. The reverse really.

 

This may be obvious to some, but there's nothing stopping you using voices from other games to voice your Skyrim mod.

For example, Fallout4 has a bunch of trained voice files. I think they're all a bit robotic though. The Skyrim voices seem to have better data in most cases.

I found that by default they tend to all come out with very flat tones; quite different to the Skyrim voices.

However, if you then manually tweak the tones and lengths, it starts to sound a lot more natural.

And then the UI magically loses all your length and tone edits  

ShelbieChase is probably the least robotic of the FO4 voices, and eerily similar to our beloved femaleyoungeager ... almost as if they were the same actor.

I did a little experimentation to see if they sound the same in various cases, because (due to different training data) they might come out a little different.

I didn't get any noticeable differences though.

Timing and pitch edits you make manually are much more obvious - if there's any difference at all.

[Lupine00]

7 hours ago, Monoman1 said:

Think you need another download: https://developer.nvidia.com/cuda-10.1-download-archive-base

Alas, still no working CUDA. It recognizes it OK, then fails to load the voice set.

I have some specific python paths and pytorch versions, so it's probably that, but the author is pretty vague about exactly how Python needs to be configured for it to work with CUDA.

CPU only seems to be very forgiving and just works.

 

Thing is, I have a working CUDA that I use for other applications... Hence the highly specific Python versions and PyTorch configs.

 

I'm on CUDA 11.2 ... which is latest, and matches my drivers. I've been on it for a while now with no issues.

 

That link is to the old 10.1 version that SKVA is bound to. I don't think anyone should install that, but probably SKVA needs it.

 

When I run tests from the 11.2 demo suite, everything is fine and vanilla: devicequery, bandwidthtest, busgrind, etc all coming back with PASS results and the values you might expect. I'm still thinking the problem is probably not with the CUDA setup but the Python libraries. Over 14 terraflops on NBody ... I'd imagine some people with crazy OCs can get over 15. Rudy Rucker expected general purpose AI around this point  

 

You can get PyTorch working with 11.2 with some pain, but that's not the version of Torch SKVA has embedded, and I know from previous experience that updating Torch version is rarely painless.

 

OK ... some more experimentation ...

 

Side by side install of 10.1 is ... sort of possible. You can only have one first in the path of course.

I tried it, and everything worked in the old demos except oceanFFT. So there are some breaking issues with 30XX and CUDA 10.1

Alas, SKVA Synth still couldn't switch to GPU without hanging, so it seems those issues are impacting it.

 

If anyone has working 30XX GPU with this, please post what you did.

 

My guess is the best approach is to upgrade the Torch libraries, but torch is terrible at backwards compatibility.

Last time I did that it required a rewrite of quite a bit of code, but that was jumping a lot of versions, and this time it's only ... two torch releases?

[Corsayr]

Hi again! ?

 

I am having an issue with licenses. When defeat triggers a robbery, or SLAdventures triggers a robbery (sleep creep), and they steal a license, SLS doesn't seem to notice the license is gone. Even though the physical license has been removed from inventory. 

 

not sure what kind of fix options there are for this. But at min would it be possible to make a check license hotkey that would force a scan of your inventory and adjust your license status? 

[Lupine00]

42 minutes ago, Corsayr said:

But at min would it be possible to make a check license hotkey that would force a scan of your inventory and adjust your license status?

Just an option in the MCM would be enough?

But if there's a consistent issue with events not firing (and I suspect there is, because inventory related events are not reliable in Skyrim) then it would make sense to check the location of the licenses periodically, and in particular when nearing city gates.

 

But we can imagine all kinds of solutions. Monoman may be aware of specifics here that make them all nonsense.

[Corsayr]

1 minute ago, Lupine00 said:

Just an option in the MCM would be enough?

But if there's a consistent issue with events not firing (and I suspect there is, because inventory related events are not reliable in Skyrim) then it would make sense to check the location of the licenses periodically, and in particular when nearing city gates.

 

But we can imagine all kinds of solutions. Monoman may be aware of specifics here that make them all nonsense.

 

I suggested that as a minimalist approach. Obviously a periodic check would be preferable but I can see the desire to not add too many scripted events like that. Maybe like a cell change event? 

[Lupine00]

Back to voice...

This is a good introduction to Tactotron. https://ai.googleblog.com/2017/12/tacotron-2-generating-human-like-speech.html

The SKVA solution is AFAICS Tacotron with some FastPitch optimization on the back end.

I don't think FastPitch is improving quality, it's actually trading quality for performance. (Maybe I'm wrong, but it seems WaveGlow is still being used, so I haven't fully grasped what FastPitch is doing).

Try the examples here: https://google.github.io/tacotron/publications/tacotron2/index.html

Totally non-robotic.

It also gives some nice clues on how to drive Tacotron to get good results.

 

There are NVidia implementations of almost all these things, by NVidia, in PyTorch, including Tacotron2, WaveGlow, etc.

 

What occurred to me is that we don't need to solve the text to speech problem.

What we really want is voice changing, not text to speech, so you can record dialog, with the emphasis and timing you want, and put it into any voice.

That's sort of possible, but it's a different discipline. Some of the same techniques apply.

 

Tacotron2 is turning text into sequences of mel-spectrograms ... you might as well say they are simply frequency-domain samples, that's really what they are in this context.

Similarly, there are tools to generate the base mel-spectrograms from an audio training set.

Tacotron2 maps the text for the training data to the spectrograms.

So, can we do the reverse mapping?

Train a data set with your own voice and then use it to perform speech to phoneme data, including timing and pitch changes.

That phoneme data is then pushed back the other way through a difference mapping to produce the alternate voice.

The phoneme spectrograms are fed into a synth, using the discovered timing and remapped pitch changes to get the alternate voice.

Initially, you'd probably still need a female speaker for female voices and a male for male voices, but the results would have the potential to be very fluent.

I think given more effort you could create male/female mappings.

Note that phoneme data is something DIFFERENT to what Tacotron is doing, because it's mapping directly to/from character sequences in ordinary written representations of voice.

 

Probably, this has already been done. Or something a little smarter. Just need to find the papers!

 

Anyway, should probably stop thinking about this. It's a rabbit hole that will mean I never get around to fixing my mods.

[sattyre]

10 hours ago, Monoman1 said:

True. Loads of possibilities. It's still tons of work though. 

I think you're right. But you know, having worked fairly extensively on voice mods, I see (potentially) fairly major issues ahead. 

 

 

 

 

 

 

Your browser does not support th

 

cool.  A lot of it sounds great.  Some of it, not so great, but I can hear the difference and how much better the lines are sounding after you have played around with them some.  I agree with Lupine, Sexist Guards would be awesome voiced