myshell-ai / OpenVoice

Instant voice cloning by MIT and MyShell. Audio foundation model.

https://research.myshell.ai/open-voice

Repository from Github https://github.commyshell-ai/OpenVoice

myshell-ai/OpenVoice Issues

Tensor size problem of se_features.pt extracted with openvoice
Updated 17 days ago1
buy the software
Updated 21 days ago1
Issue with Cloned Voice Quality – Need Assistance
Updated 22 days ago2
nltk
Updated 22 days ago7
ModuleNotFoundError: No module named 'melo.api'
Updated 22 days ago2
ModuleNotFoundError: No module named 'MyShell_OpenVoice'
Updated 25 days ago4
I would like to ask, how can I add a new language like Vietnamese. Thank you
Updated 25 days ago7
Website Demo sounds nothing like Local Demo
Updated 25 days ago3
Support arabic voice clonning
Updated a month ago1
Slow Inference with Python 3.9(For MeloTTS), fast on 3.11
Updated a month ago1
ImportError: numpy.core.multiarray failed to import
Closed a month ago2
The voice in version V2 doesn’t sound like the reference audio at all, whether in English or Chinese.
Updated a month ago3
How to decide the output audio duration
Updated a month ago3
Uzkzkj
Updated a month ago
Failed to process mp3 file
Updated a month ago2
Nowhere to download the checkpoint.pth for the se_extractor.
Updated a month ago
200 characters limit - tells to use opensource repo, but isn't this repo opensource ?
Updated 2 months ago2
Add Hungarian Language
Updated 2 months ago
I want to use Parler tts for as the base model, is it possible?
Updated 2 months ago4
se_extractor.get_se递归调用过深
Updated 2 months ago2
how to modify the interval time between two sentence?
Updated 2 months ago3
where is the BaseSpeakerTTS config file?
Updated 2 months ago2
Run this project on Ubuntu 24.04 with cuda 12.
Updated 2 months ago4
how to read a sentence twice?
Updated 2 months ago1
控制生成音频的静音长度
Updated 2 months ago3
Checkpoint missing when installing OpenVoice from GitHub using Visual Studio Code terminal
Updated 2 months ago3
Can you add a dockerfile for v2 that is equavalent on huggingface
Updated 3 months ago
Support voice clone
Updated 3 months ago
Support Persian language
Updated 3 months ago1
The tone cloning part has an ONNX model?
Updated 4 months ago
Failed to build tokenizers ERROR: Could not build wheels for tokenizers, which is required to install pyproject.toml-based projects
Updated 4 months ago
Language and Speaker ID mapping issue
Updated 4 months ago5
Falta el archivo checkpoints/base_speakers/EN/config.json
Updated 4 months ago1
se_extractor.py crashes on line 28: "segments, info = model.transcribe(audio_path, beam_size=5, word_timestamps=True)"
Updated 5 months ago2
Can I use VAD for OpenVoice2?
Updated 5 months ago2
Kernel death on se_extractor.get_se() (demo_part3.ipynb)
Closed 5 months ago2
Kernel crash in cell 3 demo_part3.ipynb openvoice v2 windows.
Closed 6 months ago4
Request for Android release. alternative google Speech Recognition & Synthesis
Updated 5 months ago
I want to run OpenVoiceV2 huggingface demo on my local GPU.
Updated 5 months ago2
How were the base models trained?
Updated 5 months ago1
Converting to JavaScript
Updated 6 months ago
FileNotFoundError: [WinError 2] The system cannot find the file specified
Updated 6 months ago1
can I use openvoice for speech to speech
Updated 6 months ago1
I have a problem about OSError: [WinError 6] Handle is invalid
Updated 6 months ago
v2 does not work well with cosyvoice TTS
Updated 6 months ago1
How do I use the weights trained on mello TTS with the converter?
Updated 6 months ago1
Docker Guide link broken
Updated 6 months ago3
Dead Kernel Demo_part3
Closed 6 months ago2
while run demo_part3.ipynb, ascii codec error occrued
Updated 6 months ago
AttributeError: 'SynthesizerTrn' object has no attribute 'enc_p'. Did you mean: 'enc_q'?
Updated 6 months ago9