Create app.py

app.py

@@ -0,0 +1,87 @@
+import gradio as gr
+import pandas as pd
+import tempfile
+import os
+from openai import OpenAI
+
+client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+# -------- Speech to Text --------
+def transcribe_audio(file_path):
+    with open(file_path, "rb") as audio:
+        transcript = client.audio.transcriptions.create(
+            model="whisper-1",
+            file=audio
+        )
+    return transcript.text
+
+# -------- Extract CRM Fields --------
+def extract_fields(text):
+    prompt = f"""
+    Extract the following fields from the conversation:
+    Name, Phone, Product, Budget, Location, Intent.
+    
+    Conversation:
+    {text}
+    
+    Return in JSON format.
+    """
+
+    response = client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[{"role": "user", "content": prompt}]
+    )
+
+    try:
+        data = eval(response.choices[0].message.content)
+    except:
+        data = {}
+
+    return data
+
+# -------- Main Processing --------
+def process_audio(audio_file):
+    if audio_file is None:
+        return "No audio provided", None, None
+
+    # Save temp file
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
+    temp_file.write(audio_file.read())
+    temp_file.close()
+
+    # Step 1: Transcribe
+    text = transcribe_audio(temp_file.name)
+
+    # Step 2: Extract fields
+    data = extract_fields(text)
+
+    # Convert to DataFrame
+    df = pd.DataFrame([data])
+
+    # Save Excel
+    excel_path = os.path.join(tempfile.gettempdir(), "crm_output.xlsx")
+    df.to_excel(excel_path, index=False)
+
+    return text, df, excel_path
+
+# -------- UI --------
+with gr.Blocks() as app:
+    gr.Markdown("# 🎙️ AI Voice to CRM Auto Filler")
+
+    with gr.Tabs():
+        with gr.Tab("🎤 Record Inquiry"):
+            mic_input = gr.Audio(source="microphone", type="file")
+            btn1 = gr.Button("Process Recording")
+
+        with gr.Tab("📁 Upload Voice"):
+            file_input = gr.File(file_types=["audio"])
+            btn2 = gr.Button("Process File")
+
+    transcript_output = gr.Textbox(label="Transcription")
+    table_output = gr.Dataframe(label="Extracted CRM Data")
+    download_btn = gr.File(label="Download Excel")
+
+    btn1.click(process_audio, inputs=mic_input, outputs=[transcript_output, table_output, download_btn])
+    btn2.click(process_audio, inputs=file_input, outputs=[transcript_output, table_output, download_btn])
+
+app.launch()