From version 1.92 onwards, you can use Byte Volcano Fangzhou's models for translation in the software. The specific activation and usage methods are as follows:

There is a free usage of 500 million tokens for opening accounts on Byte Volcano Engine between May 15th and August 30th.

Step 1: Log in & Register

Open the website https://console.volcengine.com/auth/login/. If you don't have an account, register first, and if you have one, log in directly.

Step 2: Real-Name Authentication

There is no way around this. It is a mandatory legal requirement for domestic services. If you want to use it, you have to accept it. After logging in, open the account center address and click real-name authentication.

https://console.volcengine.com/user/authentication/detail/

You can choose face or bank card authentication.

Step 3: Go to Activate and Receive Benefits

After successful real-name authentication, open the address https://console.volcengine.com/ark/region:ark+cn-beijing/openManagement until "Activation Management"

Then click any "Activate Service", select all models on the opened page, and confirm activation

Continue to click Submit

After OK, return to the activation management page and refresh to see that all have been activated

Now that it has been activated, how to use it in the code? Read on

Create API Key

Below "Activation Management", you can see the "API key" menu, click it

The last step is to create an "Inference Access Point", use this access point name instead of where you need to fill in the model

Create Model Inference Access Point

Still at this location, look up, you can see the "Model Inference" menu, click it

After clicking "Create Inference Access Point", the following interface will pop up. Fill in the access point name at will, and then click "Add Model". A large number of available models will appear

As shown in the figure below, in the model selection, it is recommended to only select the models that exist in "Activation Management", such as those models starting with Doubao-lite Doubao-pro Moon. After selecting, several model versions will appear on the right. You need to specifically select one. It is recommended to only select the version with a numeric name, such as 240515, etc.

Below is my selection

After the creation is complete, return to the "Model Inference" list page, pay attention to a string of text starting with ep, that is the "Access Point Name" to be used in the code

In code use, this name and api key are two required parameters

Using in pyVideoTrans

https://github.com/jianchang512/pyvideotrans

1. Upgrade pyVideoTrans to version 1.92+, the address is above
2. Open the videotrans/set.ini file, search for zijiehuoshan_model=, and fill in your access point name after the = sign, note that this name must be the automatically generated one

.

The effect after filling in is similar to

zijiehuoshan_model=ep-20240615073625-zrlbj,ep-41521-auyed ,

If there are multiple access points, separate them with English commas.

3. Open the software - Settings menu - Byte Volcano Engine, fill in your API key, and select the access point to use.
4. If there is no problem with the test, you can use it on the main interface

Usage Notes

For well-known reasons, you must be careful not to send or consult any sensitive questions or content containing sensitive words, as well as unhealthy content when using this model, otherwise, you will be returned "I cannot answer this question" at light, and your account will be blocked at worst.