Skip to content
TheChatArchiveThe Chat Archive
gpt4all-13b-snoozy· OpenAIHugging Face Arena Human Preference 55K

hello

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with oasst-pythia-12b’s answer.
  1. User

    hello

  2. Assistant

    Hello! How can I assist you today?

  3. User

    I want to create the 22 key forms from Azure TTS using Live2D. Explain to me how many parameters I need to create in Live2D model and how to get them driven by Azure TTS. Explain step by step.

  4. Assistant

    Hi, I can assist you with creating the 22 key forms from Azure TTS using Live2D. Here is a step-by-step guide on how to do it:

    1. Install Live2D: You need to install Live2D on your computer to create the models. You can download Live2D from the official website: https://live2d.jp/en/download/
    2. Install Azure TTS: Install the Azure Text-to-Speech API on your machine. You can download the API from the official website: https://azure.microsoft.com/en-us/services/text-to-speech/
    3. Create the Live2D model: Open Live2D and create a new model. You will need to set the following parameters:
      • Joint count: 22
      • Joint type: skeleton
      • Skeleton type: custom
      • Body type: human
      • Model: create new
      • Name: your desired name
    4. Import the Azure TTS model: Once your Live2D model is created, import the Azure TTS model to create the 22 key forms. To do this, go to the Azure portal and download the TTS model.
    5. Import the model to Live2D: Once you have the TTS model, import it to Live2D. Go to the Live2D menu and click on "Import model." Select "Import TTS model" and choose the TTS model you downloaded earlier.
    6. Export the model: Once the model is imported into Live2D, you can export it as JSON. To do this, go to the Live2D menu and click on "Export model." Choose the JSON format and save it to your computer.

    That's it! You should now have a Live2D model that is driven by Azure TTS. Let me know if you have any further questions or if I can assist you with anything else.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.