app.py

import cv2
import gradio as gr
from deepface import DeepFace
from gtts import gTTS

# Define a function that takes a webcam frame and returns facial analysis results
def analyze_face(frame):
    try:
        # Save the webcam frame as an image file
        cv2.imwrite("webcam_frame.jpg", cv2.cvtColor(frame, cv2.COLOR_RGB2BGR))
        # Use DeepFace to analyze the saved image file
        result = DeepFace.analyze("webcam_frame.jpg")
        # Extracting relevant information from the result
        dominant_emotion = result[0]['dominant_emotion']
        age = result[0]['age']
        gender = result[0]['dominant_gender']
        race = result[0]['dominant_race']
        # Construct the output text
        output_text = f"Emotion: {dominant_emotion}, Age: {age}, Gender: {gender}, Race: {race}"
        # Convert text to speech
        tts = gTTS(text=output_text, lang='en')
        audio_path = "output.mp3"
        tts.save(audio_path)
        return audio_path
    except Exception as e:
        return str(e)

# Create a Gradio interface with a webcam input and audio output
iface = gr.Interface(fn=analyze_face, inputs="webcam", outputs="audio")
# Launch the interface
iface.launch(share=True)