Starting from version 2.04, the video translation software supports dubbing using the Fish TTS API.

Deploy Fish TTS and Start API Service

Note: From pyvideotrans version v3.63 onwards, ensure that 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 the API service must be started—simply launching the web UI (i.e., opening the browser interface) is not sufficient. The default API address is http://127.0.0.1:8080/v1/tts.

For detailed deployment and API startup instructions, 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 that the API is running. Then, open the video translation software, go to the top-left settings menu → Fish TTS, and enter the corresponding API address for Fish TTS in the API field. 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 of the voice you want to use. The optimal duration is 10–20 seconds, with clear sound and no background noise. Place this audio file in the root directory of the translation software, in the same folder as sp.exe.

For example, if you want to use an audio file named 1.wav, place it in the folder containing sp.exe or sp.py. Suppose the corresponding text for 1.wav is "Hello, my dear friends."

You need to enter:

1.wav#Hello, my dear friends.

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

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, use natural line breaks; do not manually add line breaks.

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

Notes

0. Use simple English or numeric names for audio files and folders; avoid spaces. If you want to store all reference audio in a dedicated folder (created within the directory containing sp.exe), use simple English or numeric names for the folder as well, without spaces.
1. Fish-speech supports a limited number of languages; 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, switch the dubbing channel to edgeTTS first, then switch back to FishTTS.