Downloads · 30 days
0
xvasynth_cabal
Pendrokar/xvasynth_cabal
xvasynth_cabal is a text-to-speech model from Pendrokar. Use it when you need text read aloud.
Model created by Dan Ruta on the user Pendrokar's request.
Access
Public
Updated Jun 9, 2025
Repo size
227 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt227 MB · 100%
At a glance
- Task
- Text-to-Speech
- Access
- Public
- Created
- Mar 10, 2024
- Updated
- Jun 9, 2025
- SHA
- 6c84d24e
Base models
Spaces
Model card
From the Hugging Face model README
Model created by Dan Ruta on the user Pendrokar's request.
Copyrighted dataset, owned by EA at this time of writing. The dataset was used for training the fine-tuned model. The base xVASynth models also use copyrighted material, in which case all xVASynth models uploaded to HF are equally affected.
But it is impossible to use the voice itself for impersonation purposes due to the heavy robotic post-affect applied to it. Therefore the voice actor, may he rest in peace, and his family should have no qualms about the demonstrative use of this model for cloning robotic sounding voices.
Synthetic sample of model: <audio controls> <source src="https://huggingface.co/Pendrokar/xvasynth_cabal/resolve/main/cnc_cabal.wav?download=true" type="audio/wav"> Your browser does not support the audio element. </audio>
FastPitch v1.1 video demo ▶:
- Task
- Text-to-Speech
- Languages
- en, de, es, it, nl, pt
- Created
- Mar 10, 2024
- Updated
- Jun 9, 2025