Starting from version 1.92, you can use ByteDance Volcano Ark models for translation within the software. The specific activation and usage methods are as follows.
Step 1: Login & Registration
Open the URL: https://console.volcengine.com/auth/login/. If you don't have an account, register first. If you do, simply log in.
Step 2: Real-Name Verification
There's no way around this. It's a mandatory legal requirement for domestic services in China. You must accept it if you want to use the service. After logging in, open the account center URL and click on "Real-Name Verification".
https://console.volcengine.com/user/authentication/detail/
You can choose facial recognition or bank card verification.
Step 3: Activate and Claim Benefits
After successful real-name verification, open the following URL and navigate to "Activation Management": https://console.volcengine.com/ark/region:ark+cn-beijing/openManagement
Then, click on any "Activate Service" button. On the page that opens, select all models and confirm activation.
Continue by clicking "Submit".
Once done, return to the "Activation Management" page and refresh. You should see that all services are now activated.
Now that the services are activated, how do you use them in code? Read on.
Create an API Key
Below the "Activation Management" section, you will see the "API Key" menu. Click on it.
There's one final step: creating an "Inference Endpoint". Wherever a model name needs to be filled in, use this endpoint name instead.
Create a Model Inference Endpoint
Still in the same area, look up slightly to see the "Model Inference" menu. Click on it.
After clicking "Create Inference Endpoint", the following interface will pop up. Enter any name for the endpoint, then click "Add Model". A large list of available models will appear.
As shown in the image below, in the model selection, it is recommended to only choose models that exist in the "Activation Management" list. For example, models starting with Doubao-lite, Doubao-pro, Moon, etc., are all fine. After selecting a model, several model versions will appear on the right. You need to choose a specific version. It is recommended to only choose versions with numeric names, such as 240515, etc.
Here are my selections:
After creation is complete, return to the "Model Inference" list page. Pay attention to the text starting with ep—that is the "Endpoint Name" to be used in the code.
In code usage, this name and the API key are the two required parameters.
Using it in pyVideoTrans
- Upgrade pyVideoTrans to version 1.92 or above. The address is above.
- Open the
videotrans/set.inifile, search forzijiehuoshan_model=, and after the=sign, fill in your endpoint name. Note that this name must be the auto-generated one.
After filling it in, it should look similar to: zijiehuoshan_model=ep-20240615073625-zrlbj,ep-41521-auyed
If you have multiple endpoints, separate them with English commas. 
- Open the software, go to the Settings menu -> ByteDance Volcano Engine, fill in your API key, and select the endpoint you want to use.
- Test it. If there are no issues, you can start using it from the main interface.
Important Notes
As is well known, when using this model, you must be careful not to send or inquire about any sensitive topics, content containing sensitive keywords, or unhealthy content. Minor offenses may result in a response like "I cannot answer that question," while serious offenses may lead to account suspension.