xVASynth

About

xVASynth is a single player action game. It was developed by Dan Ruta and was released on January 27, 2022. It received mostly positive reviews from players.

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 the short intro/tutorial videos, narrated by various supported voices.…

Genres & Tags

Free to Play

Play Modes

Single-Player

Skip User Reviews

72%

Audience ScoreBased on 69 reviews

humor4 positive mentions

stability3 negative mentions

The software is free and offers a good combination of performance and sound quality for generating AI voices.
It has an intuitive interface for both synthesizing and training voices, making it accessible for modders and casual users alike.
The community is active, providing new voice packs and support, which enhances the overall experience.

The user interface is poorly designed and can be frustrating to navigate, leading to a steep learning curve for new users.
Downloading voice packs requires a premium Nexus account, which limits accessibility and can be cumbersome for those without a subscription.
Many voices sound robotic and lack the quality expected from modern AI voice synthesis, making it less appealing for serious projects.

humor
4 mentions Positive Neutral Negative
100%
The humor in the app is characterized by a mix of playful commentary on the community's focus on technical aspects, with users finding amusement in the contrast between the nerdy discussions and the desire for entertaining results. While some voices may come off as robotic, the moments when they sound good often elicit laughter, contributing to the app's overall comedic appeal.
- “It's quite funny that the loudest voice in this app community is trying to nerd you out about TTS/vocoder technology; sorry, but most users want the end result.”
- “Some voices are a little robotic, but when they do sound good, it is very funny.”
- “Pacing is a funny one.”
stability
3 mentions Positive Neutral Negative
100%
Users report that Xvasynth features an intuitive interface for synthesis and training, but it suffers from significant bugs that affect stability. While the arpabet pronunciation is noted as an interesting feature, the overall voice output quality is considered lacking. The web interface, despite its bugs, is still appreciated for its functionality.
- “Xvasynth does have an intuitive interface for both synthesis and training (xvatrainer), even if it's buggy. Having ARPAbet pronunciation instead of SSML (Speech Synthesis Markup Language) is very interesting, but in terms of voice output, it's lacking.”
- “It's buggy.”
- “The web interface is a bit buggy, but still awesome!”
story
2 mentions Positive Neutral Negative
50%
50%
The story aspect of the game is criticized for its poor writing quality, despite the presence of useful tools for creating quests.
- “Good tools, terrible story writing.”
optimization
1 mentions Positive Neutral Negative
100%
The software is praised for its exceptional optimization, offering a superior combination of performance, sound quality, and user-friendliness, making it more than just a "Skyrim modding tool." Users appreciate its efficiency in generating text-to-speech locally.
- “I really underestimated this software for too long as just being a 'Skyrim modding tool.' Yes, it is, but it also happens to be the best combination of performance, sound, and ease of use for locally generated text-to-speech that I have found.”
graphics
1 mentions Positive Neutral Negative
100%
Users report that the graphics performance on Windows 10 with an ASUS B450 motherboard, Ryzen 5 2600 processor, 32 GB of RAM, and an RX 6400 graphics card is satisfactory, providing a smooth visual experience in games. However, specific details about graphical fidelity or issues were not mentioned. Overall, the setup appears capable of handling modern graphics demands effectively.