Starting from version 1.92, you can use ByteDance Volcano Engine Ark's models for translation in the software. The specific activation and usage methods are as follows.

Step 1: Login & Registration

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

Step 2: Real-Name Authentication (KYC)

This is unavoidable. Domestic services are legally required to do this. If you want to use the service, you have to accept it. After logging in, open the account center address and click on real-name authentication:

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

You can choose face or bank card authentication.

Step 3: Activate and Claim Benefits

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

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

Continue by clicking "Submit."

After clicking OK, return to the activation management page and refresh. You should see that all services are now activated.

Now that you've activated the services, how do you use them in code? Continue reading.

Create an API Key

Below "Activation Management," you'll see an "API Key" menu. Click on it.

There's one last step: create an "Inference Endpoint." Use this endpoint name in place of the model where you need to specify the model in the software.

Create a Model Inference Endpoint

In the same location as before, look up slightly to find 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 number of available models will appear.

As shown below, it is recommended to only select models that exist in "Activation Management," such as those starting with Doubao-lite, Doubao-pro, and Moon. After selecting a model, several model versions will appear on the right. You need to choose a specific version. It's recommended to choose the version with a numerical name, such as 240515.

Here are my choices:

After creating, return to the "Model Inference" list page. Note the string of text starting with ep. This 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 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 enter your endpoint name after the = sign. Note that this name must be the automatically generated one.

.

An example after filling it in:

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

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

3. Open the software, go to the "Settings" menu, and then "ByteDance Volcano Engine." Fill in your API key and select the access point to use.
4. Test and if there are no problems, you can use it in the main interface.

Usage Notes

Due to well-known reasons, be careful not to send or inquire about any sensitive issues or content containing sensitive words, as well as unhealthy content, when using this model. The result could range from a returned "I cannot answer this question" to account suspension.