File size: 2,023 Bytes
2368c75
 
 
 
 
1b365e4
2368c75
 
1b365e4
2368c75
 
 
 
 
 
 
 
 
 
 
 
 
1b365e4
2368c75
1b365e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2368c75
 
1b365e4
 
2368c75
 
 
 
 
 
1b365e4
 
2368c75
 
 
 
1b365e4
2368c75
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
import streamlit as st
import speech_recognition as sr
from transformers import pipeline
import requests

# Load the chatbot model from Hugging Face
chatbot = pipeline("conversational", model="facebook/blenderbot-400M-distill")

# Function to convert speech to text using SpeechRecognition
def speech_to_text():
    recognizer = sr.Recognizer()
    with sr.Microphone() as source:
        st.info("Listening...")
        audio = recognizer.listen(source)
        try:
            text = recognizer.recognize_google(audio)
            return text
        except sr.UnknownValueError:
            return "Sorry, I could not understand the audio."
        except sr.RequestError:
            return "Speech recognition service is not available."

# Function to generate avatar video using D-ID API
def generate_avatar_video(text_response):
    api_url = "https://api.d-id.com/talk"
    headers = {
        "Authorization": "Bearer YOUR_API_KEY",  # Replace with your D-ID API Key
        "Content-Type": "application/json"
    }
    payload = {
        "script": {
            "type": "text",
            "input": text_response
        },
        "source": {
            "avatar_id": "your_avatar_id"  # Replace with the desired avatar ID
        }
    }
    response = requests.post(api_url, headers=headers, json=payload)
    video_url = response.json().get("result_url")
    return video_url

# Streamlit app interface
st.title("🗣️ Voice-Enabled Live Video Chatbot")

# Button to start recording
if st.button("Speak"):
    user_input = speech_to_text()
    if user_input:
        st.write(f"**You:** {user_input}")
        
        # Generate chatbot response using NLP model
        bot_response = chatbot(user_input)
        response_text = bot_response[0]["generated_text"]
        st.write(f"**Bot:** {response_text}")
        
        # Generate avatar video with the bot's response
        video_url = generate_avatar_video(response_text)
        
        # Display the video response
        st.video(video_url)