File information

Last updated

Original upload

Created by

Dan Ruta

Uploaded by


Virus scan

Some manually verified files

Tags for this mod

About this mod

xVASynth is an AI tool for generating high-quality voice acting lines using voices from video games. The app supports hundreds of voices, across dozens of games, and provides pitch, duration, and energy control at per-letter granularity.

Permissions and credits
Quick intro

xVASynth is an AI based app for creating new voice lines using neural speech synthesis. The app loads models individually trained on character voice data from games. The app gives users control over details such as pitch and durations of individual letters to provide control over emotion and emphasis. To see it in action, watch these short intro/tutorial videos, narrated by various supported voices:

Supported games

Twitter: @dan_ruta

Preface: The tool does not re-distribute any game assets, nor does it interact with them in any way. Game assets are used only during voice training as a reference, to guide the algorithm to drive itself to a point where it can create voices that sound similar enough to the examples. Think about it as an automated digital impersonator. Regardless, avoid using the tool in an offensive/explicit manner. Make it obvious where you can, in descriptions that the voice samples are generated, and are not from real human voice actors. Any issues you cause with this are on you.


xVASynth (or [HK]VASynth, for [Humankind] voices) is an AI app that generates voice acting lines using specific voices from video games. It can do text-to-speech (TTS) from text input, or speech-to-speech (S2S) from audio input. The app uses FastPitch [1,2] models, which give users artistic control over pitch, duration, and energy values for every letter in the audio. They also allow generating audio with explicitly defined pronunciation via ARPAbet [3] notation.

The use of neural speech synthesis leads to natural sounding voices, something which is very difficult to do with more traditional methods involving concatenations of existing data. It also means new vocabulary can be generated, outside of what the voice actors have already read out.

Speech to speech

The app can also do speech-to-speech, rather than text-to-speech. In this mode, you can provide a reference dialogue line, and have the app try to infer all the pitch/energy/duration values from the audio, for each text character. You can provide the exact text transcript of the reference audio in the input textarea, or you can leave it blank to have the app try to infer the text also. You can provide a reference audio line by recording with your microphone (by clicking the icon), or you can drag+drop an audio file onto the icon. You must first select an INPUT voice model, which must sound as similar as possible to the reference audio, and it must be a v2 model.  

ARPAbet pronunciation

You can specify exact pronunciation for words by using ARPAbet notation between { } brackets in the input, or by managing words in your own (or other people's) dictionaries. Included is CMUdict with 135k words with American-English pronunciations.

Other 3rd party dictionaries you can install into the app include:

xVADict community project - Elder Scrolls edition:
xVADict is a community project to create ARPAbet pronunciation dictionaries, for use in xVASynth. This page contains the dictionary for the unique words found across all Elder Scrolls games.

Batch Mode

For larger projects, where you need to synthesize a large amount of lines, you can alternatively use the Batch synthesis mode. You can use either a .txt file or a .csv file to batch generate hundreds or even thousands of lines, in one go, with parallelization. Although the pitch/duration/energy editor is sometimes needed to get a line sounding just right, it's sometimes not needed, and this is a good way to get an initial pass on lines. Using the GPU is especially highly recommended for this, as you can greatly parallelize the number of lines generated in one go (limited by VRAM). You should also check the various settings, such as multi-threading, to get the best possible speed out of this for your system.

3D Voice embeddings visualizer

The 3D voice embeddings visualizer is an interactive panel where you can explore in 3D all the voices in the app, as seen by an AI representation learning model, projected down to 3D. There are no axes, and this serves purely as a visualization, to enable voice discovery. You can colour the points by game, or gender, and you can enable disable specific games/voices. You can load a voice by clicking it and the "Load" button, if it's installed.

Third party plugins

The app supports third-party plugins for either/both javascript front-end (UI) and python back-end (AI) parts of the app. Plugins are a great way to customise the app to your liking, or to add new functionality to it that would be too niche or too game-specific to add to the base app for everyone. Plugins can be made for either/both the front-end/back-end of the app. Some example plugins are listed here (let me know if you make anything, and I will add it here): 

.lip and .fuz plugin for xVASynth v2:
A plugin to create .lip and (optionally) .fuz files automatically from audio lines generated with xVASynth, in either normal mode or batch mode, with or without multi-threading. DOES NOT NEED THE CK. Works for Skyrim, Fallout 4, Fallout 3, and Fallout New Vegas.

xVASynth plugin - Romanian Language:
A demo plugin for v1.4.0+ of xVASynth, where third party plugins are now supported. This plugin changes the app front-end, swapping the UI language to Romanian. Full developer reference:

If you are a developer and are interested in developing a plugin, check out the documentation here:

Nexus API integration

xVASynth has Nexusmods API integration to display what voices are available for updates/download, from any of the nexus pages listed in the "Manage Repos" sub-menu. If you have Nexus Premium, you can also download or batch download voices straight from within the app, and have them installed automatically. 

App installation

You may need to install Microsoft Visual C++ Redistributable if you don't already have it. To install the app, download it and extract it anywhere you'd like (it does not need to be in any game directory). You can optionally download the WaveGlow models (and place the files in ./resources/app/models), if you'd like more options for the vocoder used, but the bespoke HiFi-GAN vocoders included with each voice are almost always the highest quality vocoders, and by far the quickest. Launch the app by double-clicking the xVASynth.exe file. If you have any issues, try running it as admin, but be mindful that Electron on Windows has some issues with drag+drop events when running as Admin.

Important: Make sure you click "Allow" if windows asks you for permission to run the python server. I use a local HTTP server to enable communication between the python code (for the AI models) and the JavaScript code (for the Electron front-end). If there are any issues, check the server.log/app.log files (located next to xVASynth.exe) - there should be an error at the end which I'll need to see for helping with issues.

Voice installation

The recommended way to install voices is through the Nexus API integration. However, if you don't have Nexus Premium membership, or you'd prefer manual installation, you need to download the individual .zip files from the game-specific nexus pages (such as this one) and extract the voice files into the app directory, at this location: <.exe location>/resources/app/models/<game>     where <game> is the game ID. The voice .zip files already contain the required directory structure, so all you need to do is drag+drop the extracted "resources" folder from the .zip files into the folder where the xVASynth.exe file is (replacing files if prompted).

To confirm, when installing voices, you should see 4 files (a .json, a .pt, a, and a .wav file) all named as the voice you're downloading, in <your xVASynth install directory>/resources/app/models/<game>/   (where <game> is humankind, for models on this page).

Important: If you move the app files to a different directory, you MUST update the model paths in the settings, because these folder paths get initialized with the full path (starting from the drive letter) - basically, just make sure the app is looking in the new place where your models are, rather than the old folder. The app also allows you to set a different folder to store your voice models in, rather than nested in your app installation directory. The easier thing to do long-term would be to find somewhere not in your app installation folder to store your models, and set the app file paths to point there.

The voices

For Humankind, the voices trained so far (more are coming) are as follows ("Track" the mod for updates):
  • 🌮 🗲 Narrator

Where green text colour represents good quality, yellow means ok quality, and red currently quite bad (will need a good deal of playing with the input to get something good). There are several types of models and variants of models supported by the app, so I will use emojis to try to clearly label what type of model each voice is:
🌮 - This means the data for the voice is pre-trained using Tacotron2 [6], and the sentence structure/composition quality will be high 
🗲  - This means the voice comes with a bespoke HiFi [4] vocoder model, meaning the audio quality will be high 
   - This means the voice model is FastPitch1.1, enabling energy control, speech-to-speech, and ARPAbet pronunciation. Tacotron2 isn't needed for this. (rad icon for RAD-TTS the built-in alignment mechanism replacing Tacotron2)    
Note: To start with, most voice models will be v1.0 FastPitch, but they will eventually all be re-trained with the better v2.0 models with all the new features. I have over 425 voices to get through, so it may take a while.

You can optionally install WaveGlow [5] models from here, for extra vocoder options, but these are much slower, and almost always not as good as HiFi-GAN. 


The most important thing to keep in mind is to make sure to play around with the editor, to get the best quality from the generated lines. If some words/letters sound bad, try changing the pitch/duration/energy values. Tinny artefacts can normally be fixed by slightly shortening the durations of offending letters. If you absolutely can't get it to say it well, and ARPAbet pronunciation doesn't help, try re-wording the line.

Check out the community guide here, where anyone can add their tips/advice for how to get the best quality out of the tool:  You can also access this from the info (i) menu in the app.

Downstream uses
If you make anything with this tool (mod or otherwise), let me know and I will include it here.


YouTube playlist of xVA experiments (WaveGlow MaleSlyCynical):

Radio New Vegas GPT-3:

[Fallout 4] Flashy(JoeR) - Gun For Hire - Commonwealth Mercenary Jobs:
Gun For Hire allows you to open a business outside of Diamond City and to run never-ending jobs for clients from a base of 27 different archetypes.

[Fallout 4] Subversion - The Institute-Railroad Alliance Alternate Ending
An immersive alternate Railroad and Institute ending that allows the reformation of the Institute and peace between the Commonwealth factions. Free the synths, end the kidnappings, stop the immoral experiments, pacify the Brotherhood of Steel with less violence. 4 new companions are available: Z1-14, Glory, Super Mutant Virgil, Synth Elder Maxson.

[Fallout 4] Fallout 4 Office Drama Simulator - An Immersive Pre-War Roleplaying Mod
Three years before the Great War broke out, before little baby Shaun was ever conceived, his parents Nate and Nora were briefly employed in a promising tech company founded by one of Preston Garvey's ancestors, Tyrone Garvey. But it wasn't always a smooth ride in the cutthroat world of corporate politics. Enjoy this pre-War roleplaying mod / TC.

[Skyrim] Auto Sleep For Me Now
The most vanilla follower detect player auto sleep ever

[Skyrim] Sit For Me Now
Your follower auto sits with you

[Skyrim] Me So Hungry:
NPCs cooking

[Oblivion] Chapter II - Daggerfall 3E433
Welcome to the Kingdom of Daggerfall, Experience the entirety of Hammerfell & High Rock recreated lore friendly with Chapter II Content

[Fallout 4] Marked for Termination - A Terminator-Inspired Manhunt in the Commonwealth 
In the future the Sole Survivor of Vault 111, you, will lead mankind in a war against a malevolent artificial intelligence programmed to enslave the world. From this dark future two machines have been sent back, one to kill you, the other to protect you. Live or die... war never changes.

[Cyberpunk 2077] All Rhino All the Time:
Complete AUDIO AND VISUAL overhaul for various characters into the large muscular beauty, Rhino. Some have options for new skin, hair, and clothes, and some also have reworked female voices (via CPVA Synth).

[Skyrim] Phenderix Magic World:
Phenderix Magic World adds a massive amount of content including new spells, weapons, bosses, followers, locations, and much more! Download today to unleash hundreds of new roleplaying options and discover a new world where magic has just begun to awaken.

[Skyrim] Wedding Outfit Commission:
Getting married? Commission wedding outfits for yourself and your spouse from Radiant Raiment! Now you and your betrothed can get hitched in style. (Fully voiced with brand new immersive dialog created using xVASynth)

[Skyrim] I'm Glad You're Here - a follower and spouse appreciation mod: (LE)
Allows the player to show their appreciation to their followers, spouse and adopted kids by dialogue and a hug animation. Voiced with vanilla assets.

[Skyrim] Less Generic Housecarls - Argis (Markarth) Dialogue Expansion and Quest
Dialogue expansion and personal quest for Argis the Bulwark, your Markarth housecarl.

[Skyrim] Afterlife - Resurrected:
Afterlife for NPCs is back! Valiant Nords will go to Sovngarde, while soul trapped characters will be sent to the Soul Cairn, upon death.

[Skyrim] Blood on the Ice- Wuunferth Dialog Fix:
Fixes a couple of inconsistencies with Wuunferth's dialogue during the quest 'Blood on the Ice'. ESL- flagged!

[Skyrim] Dovahsil - Alduin's Faction
This mod is designed to add another option to the end of the main quest: Siding with Alduin, burning down Sovngarde, and destroying the Blades.

[Skyrim] Dealing with Daedra (LE)
Warlock style magic systems and new factions. Magic systems offer power for a price to non-mage characters. New factions provide "quests" and gameplay hubs. Aimed at creating new character build opportunities.

[Fallout 4] Nuka-World Reborn
Nuka-World Reborn is a quest mod which not only allows you to have multiple options to get rid of the raiders, but it adds new questlines to Nuka-World and allows you to play as a Trader.

[Fallout 4] Viva Nuka-World
The sequel to Nuka-World Reborn - Viva Nuka-World is set after the events of Nuka-World Reborn, offering a more rigid quest design, more detailed dialogue scenes, configuration options and more...

[Skyrim] Positive Undressed Reactions:
New lore-friendly voiced reactions to the player being undressed, using xVASynth, unused lines and splicing.

[Skyrim] Daejanggeum
1. ESL, Fully voiced perfect healer, main quest helper. 2. There are story quests. and light scripts(never heavy). 3. Lite mod with only heals, no voice, no script at all.

[Skyrim] The Windhelm Smelterworks:
The Windhelm Smelterworks adds an industrial scale smelterworks outside Windhelm, bringing some depth and immersiveness to Skyrim’s heavily mining dependent economy

[Skyrim] Cait in Skyrim
Bring Cait from Fallout 4 to Skyrim. Fully voiced using Cait's voice! Currently has 79 voiced lines. I've recreated a number of the original lines from Fallout, some "tweaked" ;) and a LOT of new lines!

[Skyrim] The Elder Scrolls Legends Imports
Adds references to Elder Scrolls: Legends cards and story into the world of Skyrim.

[Oblivion] NewCity_SI_Passwall_ENG:
Here you have the Russian mod NewCity Passwall, fully translated into English

[Skyrim] Ysolda Roasts Jon
Recreates the famous "Lamar Roasts Franklin" scene with a skyrim flavor using Ysolda and Jon Battle Born

[Skyrim] Dyudyaev-Kun:
Adds a Male Woodelf dragonborn to your game.
He is a custom voice follower based on the Male young eager voice. ( use SKVA Synth)

[Skyrim] Nether's Frea:
A complete overhaul to Frea including new voiced dialogue, quest and location awareness, dynamic lines from player actions, npc interaction, combat enhancements, new abilities, non-combat bonuses, customized skin, sculpted face and more! A Frea overhaul like you've never seen before.

[Skyrim] Nether's Karliah:
A complete overhaul to Karliah including new voiced dialogue, quest and location awareness, dynamic lines from player actions, npc interaction, combat enhancements, new abilities, non-combat bonuses, customized skin, sculpted face and more! A Karliah overhaul like you've never seen before.

[Skyrim] Nether's Eola:
A wickedly macabre, darkly humorous re-imagination of Skyrim's Eola. Features an enhanced, tweaked follower with plenty of options, an additional follower by the way of Nimphaneth (wood elf cannibal necromancer), extensive idle interactions between Eola and Nimph (if you use them both), harvesting of "tasty meat" from humanoids and MUCH MORE!

[Skyrim] Bards Reborn Student of Song Become a Bard Expansion with Bard Spells:
This mod give the Bards College a massive makeover, adds a new study quest, new bardic spells, and a new character to flesh out your experience as a Bard. It includes all the great features of Become a Bard and expands on their use in the game.

[Skyrim] Authentic Sinding Follower SE:
Gives Sinding a whole visual makeover and makes him a potential follower if you decided to help him during the Daedric quest "Ill Met by Moonlight".

[Skyrim] Susena Steel-Wolf Follower:
Add Susena Steel-Wolf to Skyrim. She is staying at the Silver-Blood Inn in Markarth. She is the toughest mercenary in Skyrim. She has additional voices using SKVA Synth - xVASynth and has as much dialogue as Teldryn Sero. Her voice type is FemaleYoungEager.

[Skyrim] Random Guard Dialogues
New funny and random voiced dialogues for guards made with xVA-Synth

[Skyrim] Nazeem as a Follower:
Nazeem as a follower, but with the assistance of XVASynth to give him voiced dialogue.

[Morrowind] Voicelines for Nord Fighters Guild Males:
Voicelines for Nord males of the Fighters Guild. They will address you as Journeyman to Master with different lines depending on your disposition.

[Skyrim] Stop right there criminal scum
A mod to add the infamous Oblivion line to Skyrim guards

[Skyrim] Female Hirelings
There is only one female Hireling in Skyrim. This makes *all* of them female (just Belrand atm). Fully voiced with natural looking faces.

[Skyrim] Trigger King Olaf's Festival Any Day - With Proper Ending SE:
With this mod you can tell Viarmo to spontaneously arrange a festival on the same night. Also makes sure that each festival will automatically end at 4AM

[Skyrim] Your Choices Matter - A Dark Brotherhood Expansion
: (LE)
This mod extends the Dark Brotherhood questline in many ways and adds an optional alternate ending. The ending you get will depend on the choices you, the Player make, throughout the story. Completely voiced dialogues, using vanilla and xVASynth assets.

[Skyrim] Adoption without Murder (Innocence Lost for Good Guys):
A tongue-in-cheek alternative solution for Innocence Lost, for when you maybe want to adopt an orphan but without all that murder and stuff.

[Skyrim] Female Hirelings:
There is only one female Hireling in Skyrim. This makes *all* of them female (just Belrand atm). Fully voiced with natural looking faces.

[Skyrim] M'aiq The Liar Anniversary Edition (aka Modder's Edition):
Adds additional quirky not-quite-but-almost-fourth-wall-breaking dialogue lines to M'aiq the Liar celebrating 10 years of modding Skyrim.

[Skyrim] Thogra gra-Mugur - Orc Follower and Quest:
Help an Orc widow get revenge on the one who wronged her. Multiple body options, custom dialogues, a quest with different endings, and more! Compatible with SE and AE.

[Skyrim] Fjotra Sybil of Dibella as a Young Adult:
The new Sybil of Dibella is now a young adult, fully voiced and with a new quest.

[The Witcher 3] New Quest - Strange things:
New story about Ciri from another world.
Created using Radish Modding Tools.
P.S. My amateur quest.

[Skyrim] Serana Relationship Revamped:
A mod that aims to enhance Serana as a character and her relationship with the player character. The intent is to stay as faithful to Bethesda's original rendition while exploring new avenues of conversation and a gradually evolving relationship, either platonic or romantic which is based on how the player character interacts with her

Future Plans

Generally the plan is to keep going down the fairly long list of voices remaining, across all supported games, and new games that get added. I do plan on returning to some the voices already released to improve them with further/re-training, especially when I update the voice training pipeline with better models, or training techniques. Right away, re-training all voices to have v2.0 models is one such priority.

There are quite a few voices left to train (across all games). You can track/vote on further progress of the models being trained on my patreon page.


The best support is using the tool, making something cool with it, and letting me know about it! Or spreading the word, to anyone that may get some use/fun out of this. Spread the word! Join the discord server, and let me know if you have any ideas/suggestions, show off something you made, or you just want to chat about all this:

Special thanks:

PTC001, Hector Medima, CinnaMewRoll, Grant Spielbusch, Sean Lyons, Charles Hufnagel, Kirill Akimov, Mister Lyosea, Anthony Crane, Rachel Wiles, Elias V, Zayde Harford, Hammerhead96 ., REN SOLUS, Jacob Porter, Squid, Strength, Majoros Kristóf, Michael Gill, John S., Roman Tinkov, Jacob Garbe, Bart Kelsey, Idiotenschnitzel, Joe Bob Slim, Mikkel Jensen, Katherine Fishwick, Youbetterwork , Steely_Muttley, Jaktt1337, Walter Weaver, David Keith vun Kannon, Bob, Imogen, Yic17, Danielle, Optimist Vamscenes, David , Hawkbat , Tom Harkness, Brandon Reynolds, Clay Rakyr, Alex East, Rory Beaker, ionite, Snoutpunk, Joshua Jones, PatronGuy , flyingvelociraptor, Edward White, crash blue, Yualien Lunaris, Sergey Trifonov, Anshela Asre, Leif , VGC-VR , David , Caden Black, Katsuki , Calvin Farage, hairahcaz, Just Becca, Solstice_, Max Loef, CHASE MCKELVY, Dollspit, SpaceD0lphin, Jonathon Barton, lord parker, PConD, Joseph Paul Dennison, Krazon, Tara Cooksey, Caro Tuts, Blythe, Snud Swimp, Tako-kun, Retlaw83, Sh1tMagnet, Yael van Dok, PorcelainShrine , Ashley Higgins, FinalFrog, Donald Bass, Hazel Louise Steele, J. Quint, Lulzar, Vahzah Vulom, Ryan W, Laura Almeida, Alexandra Whitton, Zelda Hadley, Cookie , Pseudo Immortal, My Best Friend Is A Squid, Thuggysmurf, radbeetle  

All the amazing donors, anonymous or otherwise.
Adrian Łańcucki for FastPitch and the helpful discussions on GitHub.
All the amazing researchers behind the many tools and models I've used in creating this.

     [1] FastPitch -
     [2] FastPitch 1.1 -
     [3] CMUDict -
     [4] HiFi GAN -
     [5] WaveGlow -
     [6] Tacotron2 -


Changelog now moved to the changelog panel.