Last updated 07-25-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
Deep Voice 3
Deep Voice 3 is an open-source PyTorch implementation of the Deep Voice 3 text-to-speech model from Baidu Research. It reproduces convolutional sequence learning for scalable neural TTS and ships pretrained checkpoints with audio demos for single-speaker and multi-speaker setups.
The project includes models trained on LJSpeech for single-speaker synthesis and on VCTK for 108-speaker multi-speaker generation. The demo page hosts sample audio clips, attention plots, and links to pretrained weights on GitHub.
It is aimed at researchers and developers who want a reference implementation of Deep Voice 3 rather than a hosted speech API. Training scripts, inference code, and community contributions live in the public GitHub repository.
PyTorch implementation of Deep Voice 3 convolutional sequence TTS
Pretrained single-speaker model trained on LJSpeech with public audio samples
Multi-speaker VCTK model supporting 108 speakers with demo clips
Open-source code and pretrained checkpoints on GitHub
Demo page with attention visualizations and reference paper links
Faithful open-source PyTorch reference for the Deep Voice 3 paper.
Includes both single-speaker and multi-speaker pretrained demos.
Useful for researchers comparing convolutional TTS architectures.
Not a hosted API; you train and run inference yourself.
Project maintenance depends on the open-source community.
Demo site is a research sample page, not a polished product interface.
Is Deep Voice 3 free?
Yes. Deep Voice 3 is an open-source project distributed on GitHub with free pretrained models and demo audio samples.
What datasets does Deep Voice 3 support?
The published demos include a single-speaker model trained on LJSpeech and a multi-speaker model trained on the VCTK dataset with 108 speakers.
Is this the official Baidu Deep Voice 3 release?
No. This is a community open-source PyTorch implementation based on the Deep Voice 3 paper, maintained on GitHub by r9y9.
Can I use Deep Voice 3 commercially?
The repository is open source, but you should review the project license on GitHub before commercial use.
Where do I get pretrained models?
Pretrained model links are provided on the demo page at r9y9.github.io/deepvoice3_pytorch and in the GitHub repository README.