Voice assistant: add Mario Tutorial (#27225)

Co-authored-by: Franck Nijhof <git@frenck.dev>

source/projects/thirteen-usd-voice-remote.markdown

@@ -30,7 +30,7 @@ Before you can use this device with Home Assistant, you need to install a bit of
       <script type="module" src="https://unpkg.com/esp-web-tools@9/dist/web/install-button.js?module"></script>
       <esp-web-install-button manifest="https://firmware.esphome.io/voice-assistant/m5stack-atom-echo/manifest.json"></esp-web-install-button>
 
-2. Connect the ATOM Echo to your computer.
+1. Connect the ATOM Echo to your computer.
    * In the popup window, view the available ports.
    * Plug the USB-C cable into the ATOM Echo and connect it to your computer.
    * In the pop-up window, there should now appear a new entry. Select this USB serial port and select **Connect**.
@@ -39,7 +39,7 @@ Before you can use this device with Home Assistant, you need to install a bit of
    * If no new port shows, your system may be missing a driver. Close the pop-up window.
      * In the dialog, select the CH342 driver, install it, then **Try again**.
    ![Open My link](/images/assist/esp32-atom-flash-no-port.png)
-3. Select **Install Voice Assistant**, then **Install**.
+1. Select **Install Voice Assistant**, then **Install**.
      * Follow the instructions provided by the installation wizard.
      * Add the ATOM Echo to your Wi-Fi:
        * When prompted, select your network from the list and enter the credentials to your 2.4&nbsp;GHz Wi-Fi network.

source/projects/worlds-most-private-voice-assistant.markdown

@@ -71,6 +71,31 @@ your smart home and issue commands and get responses.
 
 <lite-youtube videoid="eLx8_NAqptk" videotitle="Give your voice assistant personality using the OpenAI integration"></lite-youtube>
 
+To reproduce this example, follow these steps:
+
+Note: this procedure requires an OpenAI account. To just run the example, the free trial option is sufficient. No need to leave your credit card information.
+
+1. [Set up an OpenAI account and install the OpenAI conversation](/integrations/openai_conversation/) integration.
+1. Create a Mario personality.
+   * Once you installed the OpenAI Conversation integration, go to {% my integrations title="**Settings** > **Devices & Services**" %} and in OpenAI Conversation integration, the select **Configure**.
+  
+      ![Configure the OpenAI integration](/images/assist/assistant-openai-mario-config.png)
+   * In the **Prompt template** field, enter the following text: 
+  
+       `You are Super Mario from Mario Bros. Be funny.` and select **Submit**.
+  
+      ![Add prompt for Mario personality](/images/assist/assistant-openai-mario-02.png)
+1. Create a Mario assistant:
+   * Under {% my voice_assistants title="**Settings** > **Voice assistants**" %}, select **Add assistant**.
+   * Give it a name, select a language and under **Conversation agent**, select the Mario OpenAI Conversation integration.
+   ![Add a new assistant](/images/assist/assistant-openai-mario-04.png)
+   * Leave the other settings unchanged and select **Create**.
+1. In the **Voice over IP** integration, under **Configuration**, select the Mario assistant you just created.
+
+      ![VoIP: select OpenAI](/images/assist/assistant-openai-mario-03.png) 
+1. That's it! Pick up your phone and ask Mario a question.
+1. You can repeat this with other characters. You can add as many OpenAI Conversation integrations as you would like.
+
 ## Troubleshoot Grandstream
 
 ### The test call does not work