app.py

import gradio as gr
import speech_recognition as sr
import requests
from TTS.api import TTS
import os
import numpy as np
import soundfile as sf

# Initialize TTS model
tts = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)

# Groq API key
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

def voice_chat(audio):
    if audio is None:
        return "No audio input detected.", None

    audio_array, sr_rate = audio
    sf.write("temp.wav", audio_array, sr_rate)

    # SpeechRecognition setup
    recognizer = sr.Recognizer()
    with sr.AudioFile("temp.wav") as source:
        audio_data = recognizer.record(source)
    try:
        text = recognizer.recognize_google(audio_data)
    except sr.UnknownValueError:
        return "Could not understand audio.", None
    except sr.RequestError as e:
        return f"Speech Recognition error: {e}", None

    # Call Groq LLM
    response = requests.post(
        "https://api.groq.com/openai/v1/chat/completions",
        headers={
            "Authorization": f"Bearer {GROQ_API_KEY}",
            "Content-Type": "application/json"
        },
        json={
            "model": "llama3-8b-8192",
            "messages": [{"role": "user", "content": text}]
        }
    )
    llm_text = response.json()["choices"][0]["message"]["content"]

    # Generate TTS audio file
    tts.tts_to_file(text=llm_text, file_path="response.wav")

    return llm_text, "response.wav"

demo = gr.Interface(
    fn=voice_chat,
    inputs=gr.Audio(sources=["microphone", "upload"], type="numpy", label="🎤 Speak or upload"),
    outputs=[gr.Textbox(label="Groq Response"), gr.Audio(label="AI Voice")],
    title="📚 Speech-to-Text-to-Speech with Groq LLM and TTS"
)

if __name__ == "__main__":
    demo.launch()