Starting from version 2.04, the video translation software supports using the Fish tts api for dubbing.

Deploy fish tts and start the api service

Note: Starting from pyvideotrans v3.63, you must ensure the fish-speech version is at least 1.5.0, otherwise it cannot be used.

First, you need to deploy fish-speech (>=1.5.0) and start the api service. Note that you must start the api service. Only starting the webui (i.e., just opening the browser interface) is not sufficient. The default api address is http://127.0.0.1:8080/v1/tts.

For specific deployment and api startup methods, please refer to the relevant documentation.

Fish-speech tts project open-source address: https://github.com/fishaudio/fish-speech

Documentation address: https://speech.fish.audio

Fill in the api in the video translation software

After deployment and startup, confirm the api is running. Then open the video translation software, go to the top-left Settings menu -> Fish TTS. In the api address field, enter the corresponding fish tts api. If you haven't modified it, the default is http://127.0.0.1:8080/v1/tts.

Next, fill in the Reference Audio and Reference Text.

The reference audio is the wav audio file containing the voice you want to use. The optimal audio duration is 10-20 seconds, clear and without background noise. Please place this audio file in the root directory of this translation software, in the same folder as sp.exe.

Suppose you want to use an audio file named 1.wav. Place it in the same folder as sp.exe or sp.py. Assume the corresponding text content for 1.wav is "Hello, my dear friends."

Then you need to fill in:

1.wav#Hello, my dear friends.

If you also want to use 2.wav and wish to place it in a dedicated folder, you can create a new directory within the folder containing sp.exe or sp.py. Suppose the new directory name is wavs, and its corresponding text is "The weather is nice today, let's go swimming." Then fill in:

1.wav#Hello, my dear friends.
wavs/2.wav#The weather is nice today, let's go swimming.

If the reference text is very long, maintain natural line breaks; do not manually add carriage returns or line breaks.

After saving, go to the main interface, select FishTTS in the "Dubbing Channel" dropdown, and you will see the added reference audio in the "Dubbing Role" section.

Notes

0. Please use simple English or numbers to name the parameter audio files; do not include spaces. If you want to place all reference audio files in one folder (this folder needs to be created within the directory containing sp.exe), also use simple English or numbers for the folder name, avoiding spaces.
1. Fish-speech supports a limited number of languages. Please ensure your text is within the supported range.
2. If you added reference audio in the settings but the corresponding role does not appear in the main interface, try switching the "Dubbing Channel" to edgeTTS first, then switch back to FishTTS.