Starting from pyVideoTrans v3.99-0421, MossTTS-Nano-100M is now supported for voice dubbing.

Deploying MossTTS from Source

1. Go to the MOSS-TTS-Nano-100M official repository and follow the instructions for deployment. Then run python app.py to start the API.
2. Open the pyVideoTrans software, go to Menu - TTS Settings - MossTTS-API URL, and fill in the interface address. The default is http://127.0.0.1:18083. Then, in the character list below, fill in the reference audio files and their corresponding texts.

A reference audio refers to a WAV file you want to use for voice cloning. The ideal duration is 3–10 seconds, with clear pronunciation.

For example, if you have an audio file nverguo.wav containing a clean voice of the daughter of the emperor speaking, place it in the f5-tts folder under the pyVideoTrans software, and then fill in the corresponding text of the speech in the character text field.

nverguo.wav#Enter the spoken text here

3. Click "Test". If it shows "OK", save the settings and start using it.