Steam Community :: xVASynth

xVASynth

All Discussions Screenshots Artwork Broadcasts Videos News Guides Reviews

xVASynth

0 in Group Chat

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

Visit the Store Page

Most popular community and official content for the past week. (?)

xVASynth v3.0.0

23 May, 2023

Headline changes:
- Added support for v3 models
- Added multi-lingual support, with dropdown setting for the base language to process v3 TTS input as
- Purged old speech-to-speech system. Replaced with new v3 voice conversion system, with new python-based mic recording
- Added emotion sliders for: Angry, Happy, Sad, Surprised
- Added rich text prompt editor with code-editor-like autocompletes for languages and ARPAbet
- Added backslash lang control in sub-prompt components, allowing multiple languages per prompt
- Added voice crafting system, and support for json-only voice models
- Added style sliders, and management system
- Added backwards-compatible audio 48khz super-resolution post-processing via nuwave2 diffusion model
- Added deepfilternet2 'Clean-up' post-processing model alongside super-resolution

Post-processing:
- Added ffmpeg settings for noise reduction, with configurable parameters
- Added SR and clean-up post-processing support to batch mode
- Added de-clipping and de-clicking post-processing ffmpeg filters
- Added de-essing post-processing filter

UI Changes:
- Upgrade from Electron v2 to v19
- Added right click menu on output editor to copy ARPAbet sequence to clipboard
- Added error modals for problems with Nexus API use, printing out the full response
- More reactive Voice Conversion UI
- Auto-insert spaces at start/end of text prompts
- Made the automatic space padding configurable via user setting, and not affect the prompt box or output filename
- Ensured temporary files are cleaned out after every synthesis
- Added Tab autocompletion for selected text to ARPAbet via the g2p backend
- Added explicit error message for unsupported ARPAbet symbol
- Improved batch mode window design
- Changed default ffmpeg Hz to 44100
- Filtered out * asterisks from prompts
- Cleared old sliders editor TTS data when voice conversion is used
- Disabled useless json output for voice conversion samples
- Added more obvious styling for disabled inputs
- Removed batch fast mode
- Removed now useless 'Automatically generate voice' Voice Conversion setting
- Removed ffmpeg pre-apply setting, use as enabled going forward
- Made sliders and checkboxes theme coloured
- Added pagination to the output records, with user setting for pagination size
- Filtered out non-audio files from the output records (Keeping only wav, mp3, ogg, opus, wma, xwm)
- Removed game-specific app title changes. Only xVASynth going forward
- Changed model details (i) info window opening to click, instead of hover to enable interactivity
- Added v2 and v3 UI switching for ARPAbet symbol list displays
- Added CC-BY-4.0 category
- Added splash page with YouTube links, before the EULA
- Hidden the Endorsements/Downloads counters from the Nexus Manage Repos menu, as they do not update

Under-the-hood:
- Re-built backend environments with Python 3.9
- Add 'pfft' entries into the cmudict
- Updated 3d emb visualizer to use better v3 embedding space model
- Added ability to load multiple model instances for programmatic use of the app via local http
- Added fallback model installation debugging mode for when models are loaded with missing asset files
- Added the clean-up model as a pre-processing step for voice conversion

Fixes:
- Stopped start-up error messages being very quickly dismissed by the start-up process
- Fixed Jitter button not doing anything for zero values
- Fixed microphone recording not working for mono-only microphones
- Stopped using cached g2p words if prediction failed (blank prediction)
- Added more explicit and hopefully more robust device switching for synthesis (incl for super-resolution)
- Improved/fixed error display/logging for batch mode
- Fixed batch mode bug where pitch_amp only affects first batch line
- Fixed batch mode output_path not being shown properly
- Fixed editor issue where disabled sliders could still be moved if clicked in the right place
- Fixed dashes being ignored in ARPAbet dictionary replacements
- Fixed not all settings being reset
- [Bunglepaws] Fixed manual ARPAbet input being broken in the text processing pipeline
- Fixed 3D voice embeddings visualizer not displaying gender information correctly
- Lots and lots of other misc tweaks, fixes, and polishing

xVASynth

Does xVASynth support Arabic?

I am trying to enable Arabic TTS in Mantella. The default Piper TTS supports English only, the XTTS mod on Nexus doesn't appear to have Arabic files, so I am wondering if this tool supports more languages.

GoodSmith

17 May @ 9:37am

General Discussions

v2.3.0

28 Jul, 2022

- Added xVATrainer-like metadata.csv support for batch mode input
- Added prompt text into the out samples list rows
- Added confirm window for choosing which values to reset
- Added records search based on actual prompts in jsons
- Added Save to CSV in the batch menu, to export all lines to a single file
- Fixed batch input filename case sensitivity
- Added more front-end error logging for easier user debugging help
- Fixed errors with cuda/vram usage polling
- Made alphabetical voice sorting not case sensitive
- Fixed auto-regen for letter/phoneme length
- Fixed pacing not being correctly reset
- Prevented app from clearing batch records if broken file is added on top
- Removed spaces/dots from start of filenames (security)
- Fixed pitch/energy still being editable if clicking in the same place, even when toggled not visible
- Show model json parse errors in a UI error modal
- Misc fixes
- Added community asset files for new game support: Black and White, Dragon Ball, Elden Ring, Halo, Legacy of Kain, Life is Strange, Shenmue, Starfox 64, The Legend of Heroes, The Wolf Among Us, Vampire Masquerade, Zelda; Added TTS datasets; Updated Starfield with official wallpaper

xVASynth

v2.2.0

9 Apr, 2022

- Adjusted main app UI bounds for extra space
- Added a 'Jitter' button to main app, to randomly wiggle all/selected letters/phonemes
- Added pitch amplify multiplier (Amplify/Flatten) column to batch mode
- Made the Amplify/Flatten, Raise/Lower buttons take bigger steps
- Fix for the audio player sometimes having issues with the pitch/pacing - Pull request credit: ionite
- Added setting+option to only highlight models above a specific version, in the voices list panel
- Added more robust server killing, on app exit
- Added arpabet-replace pre/post event for plugins
- Added plugins ability to cache data into the context for across multiple executions
- Added google drive link to asset files for Steam users, where assets files can't be published
- Added persistance to window position on desktop
- Added strict "" searching to ARPAbet menu
- Added .lip and .fuz renaming, for if the plugin is used
- Better UI scaling for the ARPAbet menu
- Stopped trimming spaces from beginning/end of text sequence to allow space starts/ends
- Fixed some plugin context data writing not being used by the app
- Misc fixes and tweaks
- Stopped spam from occasional ARPAbet dict re-loading
- Fixed issue where changes in the ARPAbet dictionaries would break repeat synths
- Made batch mode output paths default to using ./ prefix, if no drive letter is present
- Fixed ellipses preventing ARPAbet replacements
- 'Metal Gear Solid' game series support in the app - credit: HappyPenguin
- 'YouTube', 'Bloodborne' series support

xVASynth

Why are the voices seperate?

Can't you just add the resources for all of ur voices in the folder so i can just have access to all the voices available? just add em all

Korbe

17 May @ 3:55am

General Discussions

I can't link the software and my game.

Hello everyone. I just installed the software from steam, and when I launch it, the window opens. The software tells me that I must download the "json and pnj/jpg" files and place them in the "asset" folder. That's what I did. But when I search for my game "skyrim" there is no voice! Can someone tell me what's wrong please. Thanks in advance....

jolie-lumiere

5 Jan @ 1:10am

General Discussions

How to add voices

Now you might think. Hey, this is impossible how the heck do i add voices? Well actually it's pretty simple. Because of restrictions unless you are logged in with "NexusMods" and have a premium account you cant use the download feature: https://i.imgur.com/C3b4jBJ.png https://i.imgur.com/zYEso5D.png https://i.imgur.com/OvXACbE.png https://i.imgur.com/JDUisWC.png In this case if you DON'T have a premium subscription head over to the nexus page and go to the files section and download the ones you want: h...

Kagamine Len (鏡音リン・レ

20 May, 2023 @ 6:11pm

General Discussions

Need some help: loading... Starting up the python backend...

Wehen I starting xVASynth there is a loading screen: Loading... May take a minute (but not much more) Starting up the python backend... Its just loading endless. I tried a couple of things but nothing works.

Tetzu

26 Jan, 2024 @ 5:25am

General Discussions

See More Content

No more content. So sad.

You can help: share a screenshot, make a video, or start a new discussion!

Returning to where you were last on this page...

Cancel