DoubleCheeseburger's xVASynth Based Mod Voicification Thread

[Karkhel]

6 minutes ago, markyknoof said:

Well there is a mod on nexus right now set out to making the player character voiced in the entire vanilla game using elevenlabs to generate the player choice dialogues. And he noted that it costed to $90+ for just one voice type. As you need to pay a starting subscription, and have to pay for more characters to generate as you're only given a certain amount with your subscription. Also keep in mind this is referring to the player choice dialogues from the base game, which usually aren't multiple sentences or paragraphs of explanation at a time.  imo Elevenlabs might be viable for small mods that aren't dialogue heavy, but big stuff like babodialogue is gonna be impossible unless you're a millionaire lol

Makes sense. BTW whats the voice the mod picked? I actually wasn't sure player voice packs were possible, I only knew Text to speech mod which sadly doesn't work all that well.

[knoofofmarky]

2 hours ago, Karkhel said:

Makes sense. BTW whats the voice the mod picked? I actually wasn't sure player voice packs were possible, I only knew Text to speech mod which sadly doesn't work all that well.

The one the main author is using currently is the female Fallout 4 sole survivor voice. But there are a couple of other voice packs made by others out right now, probably more soon since the author released tools to make batch generation of the all the voice lines easier. There was also a male player voice pack but the creator (who used their own voice) took it down due to backlash iirc.

 

Main mod: https://www.nexusmods.com/skyrimspecialedition/mods/84329
Voice packs: https://www.nexusmods.com/skyrimspecialedition/mods/84814

https://www.nexusmods.com/skyrimspecialedition/mods/85731

 

 

[GermanEngineeredMachine]

2 hours ago, markyknoof said:

Well there is a mod on nexus right now set out to making the player character voiced in the entire vanilla game using elevenlabs to generate the player choice dialogues. And he noted that it costed to $90+ for just one voice type. As you need to pay a starting subscription, and have to pay for more characters to generate as you're only given a certain amount with your subscription. Also keep in mind this is referring to the player choice dialogues from the base game, which usually aren't multiple sentences or paragraphs of explanation at a time.  imo Elevenlabs might be viable for small mods that aren't dialogue heavy, but big stuff like babodialogue is gonna be impossible unless you're a millionaire lol

Absolutely a fair argument. It would be great if the tool was a buy once deal, but the limit to both number of voices, and the amount of dialogue per subscription pulls it down hard. It sounds great, but I'm willing to bet if we clone voices too well, there could even be legal issues.

[Karkhel]

27 minutes ago, markyknoof said:

The one the main author is using currently is the female Fallout 4 sole survivor voice. But there are a couple of other voice packs made by others out right now, probably more soon since the author released tools to make batch generation of the all the voice lines easier. There was also a male player voice pack but the creator (who used their own voice) took it down due to backlash iirc.

 

Main mod: https://www.nexusmods.com/skyrimspecialedition/mods/84329
Voice packs: https://www.nexusmods.com/skyrimspecialedition/mods/84814

https://www.nexusmods.com/skyrimspecialedition/mods/85731

 

 

Thanks for the links, do those work the same way usual SE voice packs do with LE skyrim? Would I just need to unpack BSA and pack it back through LE program or are there like actual scripts attached or something? Man I wish we had something like that for sexlab mods even if it was just on female voice for all. Either way thanks for showing these even if I can't use them on LE, its funny that Sexlab mods just made me generally interested in skyrim modding as a hobby even outside of lewd mods... while regular mods never did that. I guess I had to learn more myself for sexlab mods

[yacksha]

Since text-to-speech synthesis has come leaps and bounds in the last few months, primarily due to 11labs smart marketing tact, it's safe to say that anyone with patience and a will to do so can practically make voices for anything. Unfortunately due to the paywall this put a stop to almost every indie project. No one wants to pay $90+ dollars to do this HOWEVER it is not the only option for voice gen, there are many others but it seems like TortoiseTT (https://github.com/neonbjb/tortoise-tts) is the closest for now

 

11labs demonstration:

https://vocaroo.com/1av7dNQvRmGe

 

TortoiseTT demonstration:

https://vocaroo.com/1dK23oVrdY5C

 

More related to our purposes is ToirtoiseTT using a Serana model:

https://vocaroo.com/1oTV8b0yyHBc

 

I hope this doesn't get lost in the pages of this thread since this will likely be what people use as a free alternative to 11labs, while not quite as good, with a bit of fine tuning it can work well and Audacity batch processing noise removal will always clean up the rest. For those willing to give it a try, follow this guide...

 

https://git.ecker.tech/mrq/ai-voice-cloning/wiki/Installation

[devildx]

On 3/9/2023 at 2:14 PM, yacksha said:

Since text-to-speech synthesis has come leaps and bounds in the last few months, primarily due to 11labs smart marketing tact, it's safe to say that anyone with patience and a will to do so can practically make voices for anything. Unfortunately due to the paywall this put a stop to almost every indie project. No one wants to pay $90+ dollars to do this HOWEVER it is not the only option for voice gen, there are many others but it seems like TortoiseTT (https://github.com/neonbjb/tortoise-tts) is the closest for now

 

11labs demonstration:

https://vocaroo.com/1av7dNQvRmGe

 

TortoiseTT demonstration:

https://vocaroo.com/1dK23oVrdY5C

 

More related to our purposes is ToirtoiseTT using a Serana model:

https://vocaroo.com/1oTV8b0yyHBc

 

I hope this doesn't get lost in the pages of this thread since this will likely be what people use as a free alternative to 11labs, while not quite as good, with a bit of fine tuning it can work well and Audacity batch processing noise removal will always clean up the rest. For those willing to give it a try, follow this guide...

 

https://git.ecker.tech/mrq/ai-voice-cloning/wiki/Installation

Very nice but I am still waiting if the xvasynth creator will integrate some higher quality models to the app. Is so much easier to use with the script to extract the lines.

Edited March 11, 2023 by devildx

[yacksha]

7 hours ago, devildx said:

Very nice but I am still waiting if the xvasynth creator will integrate some higher quality models to the app. Is so much easier to use with the script to extract the lines.

 

Not sure what the model compatibility is between xVASynth and TortoiseTT is, but there are usually a lot of models that float by in the the /vsg/ (AI Voice Synthesis General) thread on the /g/ board (4chan). The Serana model was being passed around a few days ago, would be worth lurking to grab models as they come and keep up with the latest voice synthesis breakthoughs

[Dez65]

Love your voice packs. Wondering if I'm missing a pack you made for this mod 

 

 

Thanks for your hard work!

[Gudulba]

I am considering doing voice packs according to DoubleCheeseburger's instructions: https://www.loverslab.com/topic/168547-doublecheeseburgers-xvasynth-based-mod-voicification-thread/page/3/?tab=comments#comment-3415080

 

What's not clear to me yet:

 

- how do I know which voice packs I should download from SKVA Synth? Let's assume for example I would do an updated voice pack for Simple Slavery or Laura's Bondage Shop.

 

- his guide mentions "FonixData.cdf from Legendary Edition placed in "Skyrim Special Edition\Data\Sound\Voice\Processing" directory for lip sync (.lip) files generation;" -> is this file also mandatory if I would only do a voice pack for SE (and not for LE)? If it's mandatory, where would I get this file? I am on SE.

 

- Unfuzer CPP Edition seems to be listed as an LE mod on Nexus. Is it also compatible with SE?

[Mister X]

4 hours ago, Gudulba said:

I am considering doing voice packs according to DoubleCheeseburger's instructions: https://www.loverslab.com/topic/168547-doublecheeseburgers-xvasynth-based-mod-voicification-thread/page/3/?tab=comments#comment-3415080

 

What's not clear to me yet:

 

- how do I know which voice packs I should download from SKVA Synth? Let's assume for example I would do an updated voice pack for Simple Slavery or Laura's Bondage Shop.

 

- his guide mentions "FonixData.cdf from Legendary Edition placed in "Skyrim Special Edition\Data\Sound\Voice\Processing" directory for lip sync (.lip) files generation;" -> is this file also mandatory if I would only do a voice pack for SE (and not for LE)? If it's mandatory, where would I get this file? I am on SE.

 

- Unfuzer CPP Edition seems to be listed as an LE mod on Nexus. Is it also compatible with SE?

 

1) Do get all voice packs for Skyrim (should be sth above 80). Many mods are created in a way that multiple actors with different voices can say the same line. For all of those voices this line will have to be synthed. As you never know, which actor might or might not say a specific line, get all voice packs for Skyrim. 

 

1.1) I updated Cheeseburger's script btw, so you can load up your entire loadorder, mark all files you want and let the script run once to create all needed csv files for xVASynth:

 

2 and 3) Unfuzer or the CK aren't needed anymore with the latest version of xVASynth, there's the LIP and FUZ plugin now: https://www.nexusmods.com/skyrimspecialedition/mods/55605

That can do both, create LIP files and FUZ them their wav. Just make sure to set up xVASynth correctly

[bopmop]

Hey, is there already a Voicification for DEC SE?

DEC

 

Just in case some lists arent complete and someone has done it, before i try creating this myself.

 

[-Xiao-]

On 3/11/2023 at 12:10 PM, yacksha said:

 

Not sure what the model compatibility is between xVASynth and TortoiseTT is, but there are usually a lot of models that float by in the the /vsg/ (AI Voice Synthesis General) thread on the /g/ board (4chan). The Serana model was being passed around a few days ago, would be worth lurking to grab models as they come and keep up with the latest voice synthesis breakthoughs

 

Oh dang I made that Serana one, glad it's being shared around and put to some use. I have thought about whether or not XVASynth would work, but XVASynth was made to work with a specific type of model that takes into account prosody and text input of a certain format. I think MRQ's TTS would at best ignore that input, and at worst be completely incompatible with the program.

 

I think you'd be much better off using MRQ's UI as the new XVASynth, maybe fork it to include more batch features and maybe a simpler interface for general use, and train up a library of game character models we can all contribute to and make use of. Only thing missing from XVASynth would be that prosody sampling - it just hasn't made its way into these new models yet, so you'd have to go without that. The new models do have silent prompting, where you can prefix the speech with [Happy] and it'll read things more happily, for example.

 

If there's enough interest I might be able to help with some of this.

[Fulanoo]

On 2/7/2023 at 1:00 AM, LoverHater123 said:

Not sure if you still need it but I'll leave this here anyway since I have it hosted. It is very easy to do it yourself though!

https://anonfiles.com/AeB840W7y7/SLSFFameComments_3.31_Voice_Files_7z

Like safado said you can change the names of the BSA files to ESPs without associated BSAs. Just make sure to delete/disable the appropriate dummy ESP afterward.

The link is dead now, does anyone has a working link?

[sunhawken]

On 6/19/2021 at 3:54 PM, DoubleCheeseburger said:

How to Make Voice Files Yourself

 

This is my approach to making voice files for various mods written step by step.

During this guide I'm gonna generate voice files for Death Alternative - Your Money or Your Life for Skyrim Special Edition which comes with daymoyl.esm as an example, but the same process applies for any other plugin. Moreover, it should work Skyrim Legendary Edition and probably Fallout 4 too.

 

 

 

Getting Ready

 

Through out this guide I'm gonna be using various software.
For your convenience here is the complete list of tools I'm gonna be using:

• xVASynth for text to speech synthesis. More specifically, SKVA Synth;
• FFmpeg for post processing of generated audio files;
• xEdit (also known as SSEEdit) for exporting dialogue lines from the plugin;
• Mod Organizer 2 for mod management. Even though any other mod manager should do the job too, this guide will assume that you use Mod Organizer 2;
• Creation Kit x64 with SSE CreationKit Fixes installed and FonixData.cdf from Legendary Edition placed in "Skyrim Special Edition\Data\Sound\Voice\Processing" directory for lip sync (.lip) files generation;
• Unfuzer CPP Edition for packing .wav and .lip files into .fuz;
• Sublime Text for configuring dialogue export script (but any text editor will do too).

There are plenty of guides on the Internet on how to install every program from this list, so I'm not gonna cover this here.

 

 

 

Getting xVASynth Ready

 

It's important to configure xVASynth so it generates voice files in the appropriate for Skyrim (and probably Fallout 4) format.

 

1. Launch xVASynth.

 

2. Open settings by clicking on the cog icon on top right:

  Hide contents

 

3. Make sure that the "Use ffmpeg post-processing (requires ffmpeg >=4.3)" checkbox is checked.

Make sure that the "Audio format (wav, mp3, etc)" field contains "wav".

Make sure that the "Audio sample rate (Hz)" field contains "22050".

Make sure that the "Audio bit depth" field contains "pcm_s16le":

  Reveal hidden contents

 

 

 

Getting xVASynth Dialogue Export xEdit Script Ready

 

This is my personal xEdit script that allows to easily export dialogue lines from any plugin in the xVASynth ready format.

It also offers easy way to update voice files whenever plugin or xVASynth voice list get updated without necessity of doing the whole process from scratch by creating cache files.

 

 

Installation

 

1. Download archive from this post.

2. Unpack it into your xEdit folder next to other scripts. In my case it's "F:\Program Files (x86)\SSEEdit\Edit Scripts".

 

 

Configuration

 

Before you can use the script there is some configuring that needs to be done.

 

1. Open xVASynth Dialogue Export.pas with any text editor. The Initialize function contains some basic script settings.

 

2. Find audioOutputPath. This is the audio output directory. Specify your desired destination where all generated audio files will be stored. I like to generate audio files directly into Mod Organizer mods folder, so in my case, since I'm doing voice files for Death Alternative, it's going to be: "D:\MO2\Mods\Death Alternative - Your Money or Your Life 7.0.1a.2 Voice Files". 

3. Find skvaVoiceIds.CommaText. This property basically contains comma separated list of available voice models in the <xVASynth Voice ID>=<Game Voice ID> format. Add or remove voices from the list according to your xVASynth voice models list.

 

4. Find maleVoices.CommaText and femaleVoices.CommaText. These properties contain the list of comma separated game voices grouped by sex. Add or remove voices from the list according to your xVASynth voice models list.

5. Optionally find filterText. If True, the script will filter out some parts of the text using the regular expressions listed below. Generally, you want to keep this variable True.

6. Optionally find cachePath. Adjust path for the cache files.

7. Optionally find outputPath. Adjust output path for the xVASynth ready batch files.

 

8. Optionally find trustedVoicedPlugins.CommaText. Specify popular mod dependencies that have their dialogues voiced. For Skyrim the default value should work just fine.

 

 

 

Creating Voice Files

 

Exporting Dialogue Lines

 

1. Launch xEdit.

 

2. Load your load order.

 

3. In the plugin browser find the mod you're making voice files for. In my case it's daymoyl.esm.

 

4. Right click on it and choose "Apply Script...":

  Hide contents

 

5. In the Apply Script popup find "xVASynth Dialogue Export" script and press OK:

  Hide contents

 

6. Wait while script does its job. The more dialogue lines in plugin the longer process will be. The process will be slower if cache file for the plugin is present, because script will have to compare each dialogue line against those contained in cache file.

One the process is completed the script will print something like this in the "Messages" tab:

  Reveal hidden contents

The generated file(s) will be placed in the "xVASynth Dialogue Export" xEdit folder. In my case it's "F:\Program Files (x86)\SSEEdit\Edit Scripts\xVASynth Dialogue Export\daymoyl.esm-1.csv".

 

 

Synthesizing Voice Files

 

Now it's time for speech synthesis using xVASynth itself.

 

1. Launch xVASynth.

2. Open batch synthesis by clicking on the table icon on top right:

  Hide contents

3. Drag .csv file made by xEdit script and drop it into xVASynth's drop zone.

Output directory doesn't matter as the .csv contains all the necessary path information.

5. Once .csv file is processed, press "Synthesize Batch" and wait while xVASynth does its job.

  Reveal hidden contents

xVASynth will start generating .wav files.

 

 

Creating Lip Sync Files

 

1. Activate mod that contains voice files in Mod Organizer 2. If you don't see it, select any mod in the left pan and press F5.

 

2. In Mod Organizer 2 configure new executable for Creation Kit. In the "Arguments" field type -GenerateLips:<Plugin name>. In my case it's "-GenerateLips:daymoyl.esm". My final executable settings looks like this:

  Hide contents

 

3. Launch new Creation Kit executable. Creation Kit will start to generate .lip files for the specified plugin. Generated files will be placed to the overwrite mod. In my case it "C:\Users\admin\AppData\Local\ModOrganizer\SkyrimSE\overwrite\sound\Voice".

 

4. Eventually Creation Kit will go through all dialogue lines and close itself. Now it's time to verify the result.

First, compare number of files in xVASynth output directory with number of files in Creation Kit output directory. In my case it's  "D:\MO2\Mods\Death Alternative - Your Money or Your Life 7.0.1a.2 Voice Files\sound\Voice\daymoyl.esm" and "C:\Users\admin\AppData\Local\ModOrganizer\SkyrimSE\overwrite\sound\Voice\daymoyl.esm". Ideally, both numbers should be the same. But sometimes Creation Kit refuses to generate .lip files for some reason. There is no unified process of figuring out why this happens. In most cases it's due to faulty dialogue conditions. Some plugins modify dialogue lines from the original Skyrim (which is weird on itself considering that original voice line will remain untouched), in this case Creation Kit won't generate .lip file too.

 

5. Once everything is verified and resolved, copy .lip files from Creation Kit output directory ("C:\Users\admin\AppData\Local\ModOrganizer\SkyrimSE\overwrite\sound\Voice\daymoyl.esm" in my case) to xVASynth output directory ("D:\MO2\Mods\Death Alternative - Your Money or Your Life 7.0.1a.2 Voice Files\sound\Voice\daymoyl.esm") respecting the folder structure. If everything is done correctly every .wav file will be paired with the .lip file:

  Reveal hidden contents

 

 

 

Packing Files in .fuz

 

1. Launch Unfuzer.

 

2. Point it to the earlier created Mod Organizer 2 mod folder in the "Folder to parse" option. In my case it's "D:\MO2\Mods\Death Alternative - Your Money or Your Life 7.0.1a.2 Voice Files".

 

3. Make sure that "Parse subfolders", "Recursively" and "Process .lip files" checkboxes are all checked.

 

4. Press "Refuz (Wav->Xwm->Fuz)".

 

Unfuzer will start to pack .wav and .lip pairs into single .fuz file.

 

 

Finishing

 

All done! Your mod should be voiced now.

Previously generated .csv file(s) (in my case daymoyl.esm-1.csv) can be (and probably should be) deleted now. But keep cache file in the "Edit Scripts\xVASynth Dialogue Export\cache" folder. It will come handy when you decide to update voice files for new version of the mod or new xVASynth voices.

 

Optionally share your work with others. 

 

 

 

 

 

 

 

xVASynth Dialogue Export v3.2.zip 7.36 kB · 388 downloads

Can you also add that if the .esp has .esp masters use wyre bash too change the .esp too .esm then back too .esp when done!

[Gudulba]

I think that in the Spank That Ass voice pack, every now and then it sounds like a child is speaking, even when the same NPC just before used a different voice (I particularly remember the phrase "Damn you" in this context).

 

How is this possible? And could it be changed somehow?

 

 

[poporaltemporal]

I would request your made voicepack for Bimbos of Skyrim for several reasons:
- Its quite popular mod.
- There seems to be only one incomplete version for older release now that lacks most lines..  The incomplete version can be found here.

* Sadly the mod has some badly written lines but hey I am not native english speaker either so the inperfect are quite ok.

If there is newer voicepack for any other author for BoS and you are aware of it please let me know. Thanks.

[MasterGunner124]

This is a great set of mods. I was going to request this. Have you voiced any more mods for Skyrim? I would love to learn how you did this. I have the tools XVSynth I just do not know how to grab the text or how to assign it to each npc.

I do know it took a lot of work so I send you a huge  Thank you.

BTW do you have a Patron >

"G"

[warhead321]

Is there a pack here for Scent of Sex?

 

Just asking because I might have missed it.

[MasterGunner124]

If I remember there used to be the script you used to pull the Dialog text. Is there a way you or someone else could could re post it?

Thanks

"G"

[Mister X]

On 10/15/2023 at 8:12 AM, MasterGunner124 said:

If I remember there used to be the script you used to pull the Dialog text. Is there a way you or someone else could could re post it?

Thanks

"G"

 

[MasterGunner124]

Since I am not a true Mod-Maker I have a few questions.  If I pull the text lines and then make a few Custom Voices at say Eleven Labs How would I add them to the game. Should I replace the voice files in the Folders for the nods. In each Sound folder there are sub folders for each voice. Do I just replace the FUZ files with FUZ files in the new voice? I hope you all can understand what I am saying.

Anyway if anyone can advise me Help would be most welcome.

 

 

"I practice safe sex. I always tie my partner in the bed so she does not fall out"

[kenis19]

I really want to create my own custom audio pack additions to DOM  (Diary of Mine). Any tips?

[Cornoholio]

On 3/17/2022 at 8:07 AM, DoubleCheeseburger said:

Updated:

- SLSF Fame Comments from version 3.2 to 3.31. Download link containing updated files only: https://mega.nz/file/ayhjUQDI#bWnCH9aGGgmh_xoRFlczPl5UXs-qP2NAof00vqVEP9U. It will be available for 30 days from now.

 

 

30 days are apparently long gone... any chance for...you know?

[MasterGunner124]

Quick question for any that can help. The Script that is used to make the CVS file for VAsnyh. It I want to not generate voices I do not need make it simple say I do not want to  generate any male voices. there are a lot of references to male voices. DO I have to remove every reference to male voices. Or can I just delete the String  below this linbe

// List of voices that will be recognized as male voices

Or should I just delete this

maleVoices := TStringList.Create;

 

This is for the Male version of Follow me for sex. I would like to do the same thing for a few other mods.

 

Thanks

Edited January 8 by MasterGunner124
Added smething

[birdotron]

getting error on line 138 for the xedit script

 

cannot create file because it cannot find specified path.

slLines.SaveToFile(outputPath + pluginName + '-' + IntToStr(fileCount) + '.csv'

 

there is a path idk why it keeps giving error? or am i being stupid

 

 

edit - nope just an idiot, i forgot to add where my xedit was located on my pc oops

Edited January 17 by birdotron