This contains Text-To-Speech models for use in KoboldCpp.

**For OuteTTS:**  
You'll need 2 models, one OuteTTS model and one WavTokenizer.

**For Kokoro, Parler or Dia:**  
Download the respective model and load it into the TTS model in koboldcpp. You do not need a wavtokenizer.

**For Qwen3 TTS (legacy):**  
You'll need 2 models, one Qwen3TTS model and one Qwen3TTSTokenizer.

**For Audio.cpp models:**  
Download the respective single-file model [from this directory](https://huggingface.co/koboldcpp/tts/tree/main/audiocpp) and load it into the TTS model in koboldcpp.