ultron-ai-sdk 1.1.3 → 1.1.5

package/README.md

@@ -370,8 +370,81 @@ Set the background image of target html block in which the character is present.
 
 ```javascript
 sceneCanvas.setBackgroundImage('IMAGE_URL')
+
+```
+
+---
+
+## 🔁 Voice-to-Voice AI Wrapper Mode (`AIWrapperMode`)
+
+Your SDK can be used as a **seamless voice interface** for any AI system that accepts **text input and returns text responses**. By enabling `AIWrapperMode`, your SDK will:
+
+1. Listen to the user's **voice input**
+2. Automatically transcribe the speech to **text**
+3. Allow the developer to **forward that text to any AI API**
+4. Speak back the **AI-generated text** response using the character's voice
+
+This makes your character a complete **voice-controlled AI interface** with just a few lines of code.
+
+---
+
+### ✨ Getting Started
+
+Enable the wrapper mode:
+
+```js
+character.AIWrapperMode = true;
 ```
 
+Then add a handler to process transcribed speech:
+
+```js
+character.onSpeechTranscribed = async (text) => {
+  console.log("User said:", text);
+
+
+/////////////////////////// Your AI Workflow ///////////////////////////////////////
+  // The section below can be any API which chats with AI like openai or your own agentic API (Text to text)
+  // Send the transcribed text to your AI API
+  const response = await fetch("https://your-ai-api.com/endpoint", {
+    method: "POST",
+    headers: { "Content-Type": "application/json" },
+    body: JSON.stringify({ prompt: text }),
+  });
+
+  const data = await response.json();
+
+  const AIResponseText = data.responseText
+
+  //////////////////////////////////////////////////////////////////////////////////
+
+
+  // Speak the AI response using the character
+  character.say(AIResponseText);
+};
+```
+
+---
+
+### 🧠 Example Use Cases
+
+* Wrap OpenAI's GPT API, Cohere, or any custom chatbot backend
+* Create hands-free, conversational assistants
+* Build AI-powered characters for education, sales, or support
+
+---
+
+### 🗣️ Notes
+
+* Ensure the character has voice input and output properly configured
+* You can use `character.mute()` or `character.listen()` as needed to control flow
+* `onSpeechTranscribed` only fires when speech input has been successfully captured and transcribed
+
+---
+
+Let me know if you'd like me to include a full working example with a specific API like OpenAI or Hugging Face.
+
+
 ### Support
 
 For technical support or questions, please contact our support team or visit our documentation portal.