TensorVox Versions Save

Big release

• Added VITS PyTorch support.
• Language Standard V1, reflected in new model config JSONs, now allows for flexible addition of languages without having to change code (more relevant for developers than end users). Program can still load old models as it performs conversion.

For a VITS model, Tupac VITS has been released on the Google Drive folder. More coming.

Highly recommended that you use this release

• Some features that I forgot, but trust me, it's real good
• Lots of bugfixes and stability

New feature release.

• Now also supports Coqui-TTS
• Added ability to halt playing audio by pressing the Escape key
• Minor bugfixes

Bugfix and new feature release:

• Fixed char language values invalid for non-English langs:
• also releasing German model and "g2p" (just German character listings)
• Batch denoiser can now output specific sampling rate

As always, the release comes without any models. You'll have to grab some off the Google Drive folder, including the new Thorsten one, or train and export your own.

Mostly bugfix and minor improvement release. Still, it's highly recommended that you update.

• Fixed memory leak by threads lingering
• Made export dialog remember filenames and directories
• A bunch more improvements

Second release. Main improvements:

• Tacotron 2 support
• Full Spanish (voice, not interface) support
• Spectrogram, attention (TT2 only), waveform views
• Many bugfixes

Note that as before, this distribution is without any voice models (but does include the G2P models), so you'll have to grab some from the Google Drive folder or train and export it yourself.

First completely public release. Uses G2P-RNN and is Windows x64 only. Note: program only, to get some example models check README.