Fish Speech 1.4

🚀 Fish Speech V1.4

Fish Speech V1.4 is a leading text-to-speech (TTS) model. It's trained on 700k hours of audio data in multiple languages, offering high - quality speech synthesis across various language groups.

🚀 Quick Start

For more information about this model, please refer to Fish Speech Github. You can also check out the demo at Fish Audio.

✨ Features

• Multilingual Support: It supports multiple languages with different amounts of training data:
  • English (en) ~300k hours
  • Chinese (zh) ~300k hours
  • German (de) ~20k hours
  • Japanese (ja) ~20k hours
  • French (fr) ~20k hours
  • Spanish (es) ~20k hours
  • Korean (ko) ~20k hours
  • Arabic (ar) ~20k hours

⚠️ Important Note

You agree to not use the model to generate contents that violate DMCA or local laws.

To access the model, you need to provide the following information:

• Country
• Specific date
• Confirm that you agree to use this model for non - commercial use ONLY

📚 Documentation

Citation

If you found this repository useful, please consider citing this work:

@misc{fish-speech-v1.4,
  author = {Shijia Liao, Tianyu Li, etc},
  title = {Fish Speech V1.4},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/fishaudio/fish-speech}}
}

📄 License

This model is permissively licensed under the BY - CC - NC - SA - 4.0 license. The source code is released under BSD - 3 - Clause license.