Audio8-TTS-Realistic
More realistic speech.
More languages.
Still 0.6B.
Built on Audio8-TTS-Preview, with richer expression and support for 23 languages.
Hugging Face 
GitHub 
Paper
0.6B model parameters
23 supported languages
12 more than Preview
Listening room
A closer listen.
The same text and reference voice, rendered by five models. Start with the reference and explore the samples at your own pace.
Preview is included to illustrate the improvements in Realistic. The other models offer a broader reference for exploring different aspects of speech. Each has its own strengths; these selected examples are not an overall ranking of the models.
Showing all 24 examples
Loading listening examples…