Skip to content

Starting from version 1.92, you can use ByteDance Volcano Ark models for translation in the software. The specific setup and usage instructions are as follows.

Step 1: Log In & Register

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

Step 2: Identity Verification

This step is unavoidable due to mandatory regulations for domestic services in China. If you want to use the service, you must comply. After logging in, go to the account center and click on "Identity 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 identity 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.

Click "Submit" to proceed.

Once done, return to the Activation Management page and refresh. You should see that all services are 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 last step: create an "Inference Endpoint." Use this endpoint name wherever you need to specify a model.

Create a Model Inference Endpoint

Still in the same location, look up to find the "Model Inference" menu and click on it.

After clicking "Create Inference Endpoint," the following interface will appear. Fill in any name for the endpoint, then click "Add Model." A list of available models will appear.

As shown below, in the model selection, it is recommended to only choose models that exist in the "Activation Management" section, such as Doubao-lite, Doubao-pro, or models starting with Moon. After selecting, several model versions will appear on the right. You need to choose a specific version; it is recommended to select versions with numeric names, such as 240515.

Here is my selection:

After creation, return to the "Model Inference" list page. Note the 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 or above. The link is provided above.
  2. Open the videotrans/set.ini file, search for zijiehuoshan_model=, and after the = sign, enter your endpoint name. Note that this must be the auto-generated name.

After filling it in, it should look something like:

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

If you have multiple endpoints, separate them with commas.

  1. Open the software, go to the Settings menu, select "ByteDance Volcano Engine," enter your API key, and choose the endpoint to use.
  2. Test to ensure there are no issues, and then you can start using it on the main interface.

Usage 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 violations may result in responses like "I cannot answer this question," while severe cases may lead to account suspension.