Repository Issue Activity (beta)

#350 voxcpm2破音问题

#386 how can I install voxcpm without WeTextProcessing? / 怎样才能在安装voxcpm时不同时安装WeTextProcessing？

#372 长文本声音失真严重问题

#362 无法控制音量及每次克隆的音色不准确

#387 [Feature Request] Support for more regional languages (e.g., Tamil, Telugu, Kannada)

#384 Community project: Local-first video dubbing with VoxCPM2 + WhisperX

#357 Hallucination on very short standalone utterances (single-word Polish sentences: "tak"/"nie"/"ja")

#385 生成的语音存在 尖刺的问题

#213 Voice cutoff at the end of words — Polish language

#382 想问下在微调小众方言的时候，遇到多音字，该如何处理呢？

#361 克隆模式下4字及以下的短句合成效果异常

#377 Formalize i18n with a dedicated translation file and full English support

#375 Training WebUI: auto-download models from HuggingFace Hub

#379 Add Docker deployment with reverse-proxy streaming support

#272 VoxCPM2 Chirp/Click Artifact & Voice Consistency in One-Shot Cloning

#359 Inquiry on "is_prompt" usage in training process

#374 Concurrent TTS Performance Observation (VoxCPM2 + vLLM-Omni)

#300 Randomly Crashing without Error

#369 [audio.cpp] New audio.cpp VoxCPM2 benchmark results on the RTX 5090 --- 0.140 RTF or 6.68x realtime.

#367 连接错误

#354 Add audio.cpp as a community project for VoxCPM2. 4.34x faster than realtime on RTX 5090

#316 [Feature Request] Add support for AMD GPUs via ONNX Runtime or Vulkan

#179 关于双向流式tts

#360 instruct文本被合成出来了

#351 TypeError: VoxCPM._generate() got an unexpected keyword argument 'seed'