curl "<endpoint-url>" \
-X POST \
--data-binary '@<audio-file>' \
-H "Accept: application/json" \
-H "Content-Type: audio/flac" \

pip install gradio requests

import os

import gradio as gr
import requests

# Configuration for both endpoints
TRANSCRIPTION_ENDPOINT = "https://your-whisper-endpoint.endpoints.huggingface.cloud/api/v1/audio/transcriptions"
SUMMARIZATION_ENDPOINT = "https://your-qwen-endpoint.endpoints.huggingface.cloud/v1/chat/completions"
HF_TOKEN = os.getenv("HF_TOKEN")  # Your Hugging Face Hub token

# Headers for authentication
headers = {
    "Authorization": f"Bearer {HF_TOKEN}"
}

def transcribe_audio(audio_file_path):
    """Transcribe audio using direct requests to the endpoint"""
    
    # Read audio file and prepare for upload
    with open(audio_file_path, "rb") as audio_file:
        # Read the audio file as binary data and represent it as a file object
        files = {"file": audio_file.read()}
    
    # Make the request to the transcription endpoint
    response = requests.post(TRANSCRIPTION_ENDPOINT, headers=headers, files=files)
    
    # Check if the request was successful
    if response.status_code == 200:
        result = response.json()
        return result.get("text", "No transcription available")
    else:
        return f"Error: {response.status_code} - {response.text}"

def generate_summary(transcript):
    """Generate summary using requests to the chat completions endpoint"""
    
    # define a nice prompt to get the best results for our use case
    prompt = f"""
    Analyze this meeting transcript and provide:
    1. A concise summary of key points
    2. Action items with responsible parties
    3. Important decisions made
    
    Transcript: {transcript}
    
    Format with clear sections:
    ## Summary
    ## Action Items  
    ## Decisions Made
    """
    
    # Prepare the payload using the Messages API format
    payload = {
        "model": "your-qwen-endpoint-name",  # Use the name of your endpoint
        "messages": [{"role": "user", "content": prompt}],
        "max_tokens": 1000, # we can also set a max_tokens parameter to limit the length of the response
        "temperature": 0.7, # we might want to set lower temperature for more deterministic results
        "stream": False # we don't need streaming for this use case
    }
    
    # Headers for chat completions
    chat_headers = {
        "Accept": "application/json",
        "Content-Type": "application/json",
        "Authorization": f"Bearer {HF_TOKEN}"
    }
    
    # Make the request
    response = requests.post(SUMMARIZATION_ENDPOINT, headers=chat_headers, json=payload)
    response.raise_for_status()
    
    # Parse the response
    result = response.json()
    return result["choices"][0]["message"]["content"]

def process_meeting_audio(audio_file):
    """Main processing function that handles the complete workflow"""
    if audio_file is None:
        return "Please upload an audio file.", ""
    
    try:
        # Step 1: Transcribe the audio
        transcript = transcribe_audio(audio_file)
        
        # Step 2: Generate summary from transcript
        summary = generate_summary(transcript)
        
        return transcript, summary
    
    except Exception as e:
        return f"Error processing audio: {str(e)}", ""

# Create Gradio interface
app = gr.Interface(
    fn=process_meeting_audio,
    inputs=gr.Audio(label="Upload Meeting Audio", type="filepath"),
    outputs=[
        gr.Textbox(label="Full Transcript", lines=10),
        gr.Textbox(label="Meeting Summary", lines=8),
    ],
    title="🎤 AI Meeting Notes",
    description="Upload audio to get instant transcripts and summaries.",
)