Upload 2 files

app (1).py

@@ -0,0 +1,77 @@
+
+import os
+import gradio as gr
+import tempfile
+from groq import Groq
+import whisper
+from datetime import datetime
+import torch
+from TTS.api import TTS
+
+# Load environment variable for Groq API key
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+if not GROQ_API_KEY:
+    raise ValueError("❌ GROQ_API_KEY not found in environment.")
+
+# Initialize Groq client
+client = Groq(api_key=GROQ_API_KEY)
+
+# Load Whisper model
+whisper_model = whisper.load_model("base")
+
+# Load Coqui TTS model
+tts = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=torch.cuda.is_available())
+
+# Chat history for saving
+chat_history = []
+
+# Supported languages
+languages = {"English": "en", "Urdu": "ur", "Pashto": "ps"}
+
+# Voice-to-voice processing
+def voice_to_voice(audio_input, selected_lang):
+    global chat_history
+
+    # Step 1: Transcribe
+    transcription = whisper_model.transcribe(audio_input)['text']
+    chat_history.append(("User", transcription))
+
+    # Step 2: Groq API response
+    chat_completion = client.chat.completions.create(
+        messages=[{"role": "user", "content": transcription}],
+        model="llama3-8b-8192",
+        stream=False,
+    )
+    response_text = chat_completion.choices[0].message.content
+    chat_history.append(("Bot", response_text))
+
+    # Step 3: TTS with Coqui
+    temp_wav = tempfile.mktemp(suffix=".wav")
+    tts.tts_to_file(text=response_text, file_path=temp_wav)
+
+    # Step 4: Save chat text file
+    chat_text = "\n".join([f"{role}: {msg}" for role, msg in chat_history])
+    filename = f"chat_history_{datetime.now().strftime('%Y%m%d_%H%M%S')}.txt"
+    with open(filename, "w", encoding="utf-8") as f:
+        f.write(chat_text)
+
+    return temp_wav, chat_text, filename
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🎤 Real-time Voice Chatbot (Groq + Whisper + Coqui TTS)")
+
+    lang = gr.Dropdown(choices=list(languages.keys()), value="English", label="Select Language")
+
+    with gr.Row():
+        input_audio = gr.Audio(type="filepath", label="🎙️ Record Voice")
+        output_audio = gr.Audio(label="🤖 Bot Reply")
+
+    chatbox = gr.Textbox(label="📝 Conversation", lines=10)
+    download_btn = gr.File(label="📥 Download History")
+
+    btn = gr.Button("Talk")
+
+    btn.click(fn=voice_to_voice, inputs=[input_audio, lang], outputs=[output_audio, chatbox, download_btn])
+
+demo.launch()

requirements.txt

@@ -0,0 +1,10 @@
+
+gradio
+groq
+openai-whisper
+torch<=2.5.1
+scipy
+ffmpeg-python
+transformers
+TTS
+numpy