¶
🐸 Coqui TTS is a library for advanced Text-to-Speech generation.
🚀 Pretrained models in +1100 languages.
🛠️ Tools for training new models and fine-tuning existing models in any language.
📚 Utilities for dataset analysis and curation.
📣 News¶
Fork of the original, unmaintained repository. New PyPI package: coqui-tts
0.27.0: Caching mechanism for cloned voices.
0.25.2: OpenVoice and kNN-VC models now available for voice conversion.
0.24.2: Prebuilt wheels are now also published for macOS and Windows (in addition to Linux as before) for easier installation across platforms.
0.20.0: XTTSv2 is here with 17 languages and better performance across the board. XTTS can stream with <200ms latency.
0.19.0: XTTS fine-tuning code is out. Check the example recipes.
0.14.1: You can use Fairseq models in ~1100 languages with 🐸TTS.
💬 Where to ask questions¶
Please use our dedicated channels for questions and discussion. Help is much more valuable if it’s shared publicly so that more people can benefit from it.
Type |
Platforms |
|---|---|
🚨 Bug Reports, Feature Requests & Ideas |
|
👩💻 Usage Questions |
|
🗯 General Discussion |
The issues and discussions in the original repository are also still a useful source of information.
🔗 Links and Resources¶
Type |
Links |
|---|---|
💼 Documentation |
|
💾 Installation |
|
👩💻 Contributing |
|
🚀 Released Models |
Features¶
High-performance text-to-speech and voice conversion models, see list below.
Fast and efficient model training with detailed training logs on the terminal and Tensorboard.
Support for multi-speaker and multilingual TTS.
Released and ready-to-use models.
Tools to curate TTS datasets under
dataset_analysis/.Command line and Python APIs to use and test your models.
Modular (but not too much) code base enabling easy implementation of new ideas.
Model Implementations¶
Spectrogram models¶
End-to-End Models¶
Vocoders¶
Voice Conversion¶
Others¶
Attention methods: Guided Attention, Forward Backward Decoding, Graves Attention, Double Decoder Consistency, Dynamic Convolutional Attention, Alignment Network
Speaker encoders: GE2E, Angular Loss
You can also help us implement more models.