Video translation software version 2.04 and later supports using the Fish TTS API for voiceovers.

Deploy Fish TTS and Start the API Service

Note: From pyvideotrans version v3.63 onwards, ensure that the fish-speech end version is no lower than 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. Just starting the web UI (opening the browser webpage) is not sufficient. The default API address is http://127.0.0.1:8080/v1/tts

For specific deployment, API startup, and other operation 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 deploying and starting, confirm that the API is running, then open the video translation software. Go to the settings menu in the upper left corner - Fish TTS, and fill in the corresponding API address for Fish TTS in the API address 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 audio duration is 10s-20s, clear and without background noise. Please place the audio file in the root directory of this translation software, together with sp.exe.

If you want to use the audio named 1.wav, place it in the same folder as sp.exe or sp.py. Assume the text content corresponding to 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 want to put it in a dedicated folder, you can create a new directory in the same folder as sp.exe or sp.py. Assume 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, keep natural line breaks; do not manually add carriage returns or line feeds.

After saving, select FishTTS in the "Voiceover Channel" on the main interface, and you can see the added reference audio in the "Voiceover Role".

Precautions

0. Please use simple English or numbers to name the parameter audio, and do not include spaces. If you want to put all the reference audio in one folder (the folder needs to be created in the directory where sp.exe is located), also use simple English or numbers for the folder name, and do not include spaces.
1. Fish-speech supports a limited number of languages. Please ensure that the text is within the supported range.
2. If you have added reference audio in the settings, but the corresponding role is not displayed on the main interface, please switch the voiceover channel to edgeTTS first, and then switch back to FishTTS.