Repository Issue Activity (beta)

#261 English heteronyms aren't pronounced properly

#262 关于授权的问题

#264 能否支持p40？

#257 G2P acc

#258 Commercial use / commercial license for OmniVoice pretrained model

#233 Audio.cpp now supports Q8 GGUF and adds a new performance mode for OmniVoice; 0.0232 RTF on an RTX 5090.

#231 Feedback on running OmniVoice WebUI locally on Windows (CPU mode)

#235 Request for Commercial License – OmniVoice TTS for YouTube Content

#253 Voice cloning generation skips/drops parts of the input text

#256 Click/pop at t=0 of cloned utterances (leading spike, then silence, then speech)

#244 Clarifications on multilingual data construction (resampling, prompt-denoising, subset of data augmentation, restoration/filtering, text tokenizer) + request for implementation code

#255 When using [Auto Voice] , for the same model instance, each `model.generate()` call generates a random voice. Is there a way to consistently use the same voice?

#251 Recommended approach for concurrent serving with full parameter support

#248 What could cause inconsistent speaking speed within a single generation (~10% of the time)?

#252 Does `denoise_audio.py` produce duration-imbalanced shards?

#18 TensorRT export support?

#12 [WIP] Comfy custom nodes

#25 消费级显卡（比如5090/4090等）下的RTF统计

#246 OmniVoice Voice Cloning / Pronunciation Accuracy Issue

#204 Sometimes cut last word.

#236 Feature Request: Support Importing SRT Subtitle Files

#245 Generated audio frequently cuts off the end of the sentence

#237 Reducing Inconsistent Word Pronunciation Across Generations

#241 Support for Context Across Multiple Sentence Generation

#240 Support for Context Across Multiple Sentence Generation