Repository Issue Activity (beta)

#106 Streaming Support

#65 Support KittenTTS in ComfyUI

#151 Harmonic source: in-session nondeterminism (in-graph RNG) and float32 phase accumulation (fp16 / long-form limits)

#133 how to find such small speech to text LLM model pls but not whisper

#140 Feature: FunASR/SenseVoice for training data annotation

#84 Architecture?

#7 Training Details

#125 Ditch Python for Rust

#118 Why is misaki included in the requirements file?

#149 FEATURE: Enable the use of the system's native espeak-ng.

#71 Failed to pip install

#146 Reduce deps

#41 finetuning other language file ?

#122 German language support

#141 Golang KittenTTS Integration

#135 Please add copyright owner in LICENSE

#99 iOS demo version

#132 Hope to be able to add a function for loading local models

#126 Voice cloning support

#124 Multilingual model/Arabic support

#113 My inference setup on windows is 1GB despite the model being >100MB

#111 this is yuge, thank you

#92 Produces one single tone

#114 Not much benefit from GPU

#120 Model not using GPU (RTX 3060 Ti), running on CPU