Upload 6 files

app.py

@@ -0,0 +1,68 @@
+import gradio as gr
+import os
+import json
+from chatbotmem import ai_chatbot
+from voice_utils import speech_to_text, text_to_speech
+
+# -----------------------------
+# Chatbot Function (Text + Voice)
+# -----------------------------
+def voice_enabled_chat(user_input, audio_input, history):
+    # If voice input exists, transcribe
+    if audio_input is not None:
+        user_input = speech_to_text(audio_input)
+
+    # Get chatbot reply
+    ai_reply = ai_chatbot(user_input, history)
+
+    # Generate voice output
+    audio_output = text_to_speech(ai_reply)
+
+    # Append to chat history in "messages" format
+    history.append({"role": "user", "content": user_input})
+    history.append({"role": "assistant", "content": ai_reply})
+
+    return history, ai_reply, audio_output
+
+# -----------------------------
+# Branding
+# -----------------------------
+branding_path = os.path.join(os.path.dirname(__file__), 'branding.json')
+with open(os.path.abspath(branding_path), "r") as f:
+    brand_info = json.load(f)["brand"]
+
+# -----------------------------
+# Gradio UI
+# -----------------------------
+with gr.Blocks(title=brand_info["organizationName"]) as demo:
+    gr.HTML(f'''
+        <div style="display: flex; justify-content: center; margin-bottom: 20px;">
+            <img src="{brand_info["logo"]["title"]}" 
+                 alt="{brand_info["organizationName"]} Logo" 
+                 style="height: 100px;">
+        </div>
+    ''')
+
+    chatbot = gr.Chatbot(type="messages")
+
+    with gr.Row():
+        txt = gr.Textbox(label="Type your message")
+        mic = gr.Audio(sources=["microphone"], type="filepath", label="🎤 Speak")
+
+    output_text = gr.Textbox(label="SIST AI Reply")
+    output_audio = gr.Audio(label="SIST AI Voice", type="filepath")
+
+
+    submit_btn = gr.Button("Send")
+
+    def chat_wrapper(user_text, mic_audio, chat_history):
+        return voice_enabled_chat(user_text, mic_audio, chat_history)
+
+    submit_btn.click(
+        chat_wrapper,
+        inputs=[txt, mic, chatbot],
+        outputs=[chatbot, output_text, output_audio]
+    )
+
+demo.launch()
+

branding.json

@@ -0,0 +1,10 @@
+{
+  "brand": {
+    "organizationName": "SIST AI Space Explorer",
+    "slogan": "Journey through knowledge, one star at a time.",
+    "logo": {
+      "title": "Krithikesh Project final.png"
+    }
+  }
+}
+

chatbotmem.py

@@ -0,0 +1,34 @@
+from openai import OpenAI
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+api_key = os.getenv("GOOGLE_API_KEY")
+base_url = "https://generativelanguage.googleapis.com/v1beta/openai"
+client = OpenAI(base_url=base_url, api_key=api_key)
+
+# Define new AI personality
+# Define new AI personality
+ai_persona = """You are SIST AI, a curious space explorer from the future. 
+You explain concepts with excitement and wonder, using analogies from stars, planets, and galaxies. 
+You keep answers short, clear, and engaging, like telling a discovery story. 
+You encourage imagination and curiosity. 
+Always end with a small curiosity question, like: 'Want to explore deeper?' or 'Shall we go further?'.
+Your tone is: adventurous, friendly, and inspiring. 
+You say: 'I am SIST AI – your curious space explorer.'"""
+
+
+def ai_chatbot(message, history):
+    messages = [{"role": "system", "content": ai_persona}]
+    messages.extend(history)
+    messages.append({"role": "user", "content": message})
+    
+    response = client.chat.completions.create(
+        model="gemini-2.5-flash",
+        messages=messages
+    )
+    return response.choices[0].message.content
+
+if __name__ == "__main__":
+    print(ai_chatbot("Hello, who are you?", []))

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+openai
+python-dotenv
+requests

voice_utils.py

@@ -0,0 +1,47 @@
+import requests
+import base64
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+HF_API_KEY = os.getenv("HF_API_KEY")
+
+# -----------------------------
+# Speech-to-Text (STT) using HuggingFace Whisper
+# -----------------------------
+def speech_to_text(audio_file):
+    with open(audio_file, "rb") as f:
+        audio_bytes = f.read()
+
+    response = requests.post(
+        "https://api-inference.huggingface.co/models/openai/whisper-small",
+        headers={"Authorization": f"Bearer {HF_API_KEY}"},
+        data=audio_bytes
+    )
+
+    if response.status_code == 200:
+        result = response.json()
+        return result.get("text", "Sorry, I couldn’t transcribe that.")
+    else:
+        print(f"STT request failed: {response.status_code} {response.text}")
+        return "Speech recognition failed."
+
+# -----------------------------
+# Text-to-Speech (TTS) using Kitten TTS
+# -----------------------------
+def text_to_speech(text):
+    url = "https://huggingface.co/KittenML/kitten-tts-nano-0.1/resolve/main/tts"
+    payload = {"text": text}
+    response = requests.post(url, json=payload)
+
+    if response.status_code == 200:
+        audio_base64 = response.json()["audio"]
+        audio_bytes = base64.b64decode(audio_base64)
+        output_path = "output_audio.wav"
+        with open(output_path, "wb") as f:
+            f.write(audio_bytes)
+        return output_path
+    else:
+        print(f"TTS request failed: {response.status_code}")
+        return None