search

myshell-ai / OpenVoice

Instant voice cloning by MIT and MyShell.
https://research.myshell.ai/open-voice
MIT License
28.64k stars 2.8k forks source link

can I use openvoice for speech to speech #315

Open desis123 opened 4 days ago

desis123 commented 4 days ago

is it possible to use openvoice as speech to speech . or voice changer. If yes, can you please tell me how I can accomplish it . Thanks in advance.

dosubot[bot] commented 4 days ago

Hey @desis123! I'm here to help you with any bugs, questions, or contributions you have. Let's tackle this together!

Yes, you can use OpenVoice for speech-to-speech or as a voice changer. OpenVoice can clone the voice in the input speech audio and use the cloned voice to speak in multiple languages.

To accomplish this, you can use the already deployed services for quick use:

For a more hands-on approach, you can also try the minimal demo links provided:

For developers and researchers, you can install OpenVoice on Linux and run the provided demos for flexible voice style control and cross-lingual voice cloning. Here is a brief installation guide:

conda create -n openvoice python=3.9
conda activate openvoice
git clone git@github.com:myshell-ai/OpenVoice.git
cd OpenVoice
pip install -e .

For OpenVoice V1, download the checkpoint and follow the examples in demo_part1.ipynb and demo_part2.ipynb.

For OpenVoice V2, download the checkpoint, install MeloTTS, and follow the example in demo_part3.ipynb:

pip install git+https://github.com/myshell-ai/MeloTTS.git
python -m unidic download

Additionally, you can use the openvoice_app.py script to set up a Gradio interface for real-time voice cloning and style conversion. This script supports English and Chinese languages and allows you to select different voice styles for English. Here is a brief overview of how to use the script:

  1. Clone the OpenVoice repository and navigate to the directory.
  2. Run the openvoice_app.py script to launch the Gradio interface.
  3. Upload a reference audio file and input the text you want to convert.
  4. Select the desired voice style and agree to the terms and conditions.
  5. Click the "Send" button to generate the synthesized audio.

This setup will allow you to use OpenVoice for speech-to-speech or as a voice changer [1][2].

To continue talking to Dosu, mention @dosu.