IMS Toucan TTS project claims to support over 7000 languages for voice dubbing. After trying it out, it does work, but the quality is so-so, not excellent. It's usable if your requirements aren't high.

This project doesn't offer several fixed voice tones like edge-tts, instead, each language has a fixed tone. You can fine-tune the random tone, seed, gender, etc., using parameters like prosody_creativity/duration_scaling_factor/voice_seed/emb1.

Project address https://github.com/DigitalPhonetics/IMS-Toucan

Local Deployment Method

You can directly deploy the source code from the project website according to the instructions https://github.com/DigitalPhonetics/IMS-Toucan

I also made a Win integrated package. Those who don't want to bother can use this integrated package directly.

Download the integrated package from Baidu Netdisk and extract it to a directory, such as the D:/python/IMS-Toucan directory.

Integrated package download address https://pan.baidu.com/s/1om62tz-fmq4o5sijmHmnMQ?pwd=dck6

After extraction, you will find an espeak-ng-X64.msi file. You can install it or not. After installation, the sound quality will be better. Double-click and follow the default steps.

You will see 3 bat files in the directory. Double-click to execute them.

Start api and simple webpage.bat:

Double-clicking will start an API service and open a simple webpage, which can be used to connect to the custom TTS interface of video translation software. This API only supports the commonly used 24 languages.

The API address is http://127.0.0.1:5020/api, which can be filled in the custom TTS interface of the video translation software.

Start complete webpage ui.bat:

Double-click to start the IMS Toucan official web interface, supporting the synthesis and dubbing of all languages. Feel free to explore.

If the browser does not automatically open the page, when the terminal displays the following image, manually copy the address and open it in the browser.

Start advanced QT-ui.bat:

Double-click to start the built-in software interface. This interface is not translated, those interested can study it.

Noteworthy Issues

1. When starting, a lot of information may appear in the terminal window, as shown below. This is not an error, just ignore it.

2. After the api and complete webpage ui interface are started, the corresponding pages will automatically open in the browser, and the advanced QT will automatically open the software.

3. Sometimes, a bunch of errors may be prompted, including the Microsoft website https://docs.microsoft.com. In this case, please close the window and right-click to run the bat file as administrator.

4. The integrated package comes with built-in models, but when starting, it may check for model updates, requiring connection to https://huggingface.co. This is inaccessible from outside China, so you need a VPN. When the error contains HTTPSConnect, it means you need to use a global or system proxy.

Using it in Video Translation Software

First, upgrade the video translation software to the latest patch package. Download address https://pyvideotrans.com

After starting the software, click Menu-TTS Settings-Custom TTS Interface, and enter http://127.0.0.1:5020/api into the API address. You can fill in any letters in the role list, such as a,b,c.

After testing without problems, you can use it.