Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
coqui-tts 0.28.0.dev0 documentation
Light Logo Dark Logo

Get started

  • Tutorial for nervous beginners
  • Installation
  • Docker images
  • FAQ
  • Project structure
  • Contribution guidelines

Using Coqui

  • Synthesizing speech
    • Voice cloning
    • Voice conversion
    • Demo server
    • Mary-TTS API support for Coqui TTS
  • Training and fine-tuning
    • Training a model
    • Fine-tuning a model
  • Adding models or languages
    • Implementing new models
    • Implementing new language front ends
  • Datasets
    • Formatting your dataset
    • What makes a good TTS dataset
    • Public TTS datasets

TTS Models

  • Glow TTS
  • VITS & YourTTS
  • Forward TTS model(s)
  • 🌮 Tacotron 1 and 2
  • Overflow TTS
  • 🐢 Tortoise
  • 🐶 Bark
  • XTTS

Main Classes

  • AudioProcessor API
  • Configuration
  • Datasets
  • GAN API
  • Model API
  • Speaker Manager API
  • Synthesizer API
  • Trainer API
Back to top
View this page

Adding models or languages¶

You can extend Coqui by implementing new model architectures or adding front ends for new languages. See the pages below for more details. The project structure and contribution guidelines may also be helpful. Please open a pull request with your changes to share back the improvements with the community.

  • Implementing new models
  • Implementing new language front ends
Next
Implementing new models
Previous
Fine-tuning a model
Copyright © 2021 Coqui GmbH, 2020 TTS authors
Made with Sphinx and @pradyunsg's Furo