app.py

import gradio as gr
import requests
import json
import os
import time
from collections import defaultdict

BASE_URL = "https://api.jigsawstack.com/v1"
headers = {
    "x-api-key": os.getenv("JIGSAWSTACK_API_KEY")
}


# Rate limiting configuration
request_times = defaultdict(list)
MAX_REQUESTS = 20  # Maximum requests per time window
TIME_WINDOW = 3600   # Time window in seconds (1 hour)

def get_real_ip(request: gr.Request):
    """Extract real IP address using x-forwarded-for header or fallback"""
    if not request:
        return "unknown"
    
    forwarded = request.headers.get("x-forwarded-for")
    if forwarded:
        ip = forwarded.split(",")[0].strip()  # First IP in the list is the client's
    else:
        ip = request.client.host  # fallback
    return ip

def check_rate_limit(request: gr.Request):
    """Check if the current request exceeds rate limits"""
    if not request:
        return True, "Rate limit check failed - no request info"
    
    ip = get_real_ip(request)
    now = time.time()

    # Clean up old timestamps outside the time window
    request_times[ip] = [t for t in request_times[ip] if now - t < TIME_WINDOW]
    

    # Check if rate limit exceeded
    if len(request_times[ip]) >= MAX_REQUESTS:
        time_remaining = int(TIME_WINDOW - (now - request_times[ip][0]))
        time_remaining_minutes = round(time_remaining / 60, 1)      
        time_window_minutes = round(TIME_WINDOW / 60, 1)
        
        return False, f"Rate limit exceeded. You can make {MAX_REQUESTS} requests per {time_window_minutes} minutes. Try again in {time_remaining_minutes} minutes."
    
    # Add current request timestamp
    request_times[ip].append(now)
    return True, ""


def text_to_speech(text, accent, voice_clone_id, request: gr.Request):
    rate_limit_ok, rate_limit_msg = check_rate_limit(request)
    if not rate_limit_ok:
        return None, rate_limit_msg
    
    if not text or not text.strip():
        return None, "Error: Text input is required."

    payload = {"text": text.strip()}

    if accent and accent.strip():
        payload["accent"] = accent.strip()

    if voice_clone_id and voice_clone_id.strip():
        payload["voice_clone_id"] = voice_clone_id.strip()

    # Validate text length
    max_len = 500 if "voice_clone_id" in payload else 1500
    if len(payload["text"]) > max_len:
        mode = "Voice Cloning" if "voice_clone_id" in payload else "Standard"
        return None, f"Error: Text for {mode} is limited to {max_len} characters."

    try:
        response = requests.post(f"{BASE_URL}/ai/tts", headers=headers, json=payload)
        response.raise_for_status()

        if response.headers.get("content-type", "").startswith("audio/"):
            import tempfile
            with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
                tmp_file.write(response.content)
                return tmp_file.name, "✅ Speech generated successfully!"
        else:
            try:
                error_data = response.json()
                return None, f"Error: API returned an error - {error_data.get('message', 'Unknown error')}"
            except:
                return None, "Error: Received an unexpected response from the API."

    except requests.exceptions.RequestException as e:
        return None, f"Request failed: {str(e)}"
    except Exception as e:
        return None, f"An unexpected error occurred: {str(e)}"


# ----------------- Gradio UI ------------------

with gr.Blocks() as demo:
    gr.Markdown("""
    <div style='text-align: center; margin-bottom: 24px;'>
        <h1 style='font-size:2.2em; margin-bottom: 0.2em;'>🧩 Text to Speech</h1>
        <p style='font-size:1.2em; margin-top: 0;'>Transform text into natural-sounding human-like AI voices with low latency and exceptional quality.</p>
        <p style='font-size:1em; margin-top: 0.5em;'>For more details and API usage, see the <a href='https://jigsawstack.com/docs/api-reference/audio/tts/text-to-speech' target='_blank'>documentation</a>.</p>
    </div>
    """)

    with gr.Row():
            with gr.Column():
                gr.Markdown("#### Input")
                tts_text = gr.Textbox(
                    label="Text to Convert",
                    lines=5,
                    placeholder="Enter the text you want to convert to speech here."
                )
                
                gr.Markdown("#### Quick Examples")
                gr.Markdown("Click any example below to auto-fill the text:")
                
                with gr.Row():
                    tts_example_btn1 = gr.Button("👋 Greeting", size="sm")
                    tts_example_btn2 = gr.Button("📢 Announcement", size="sm")
                    tts_example_btn3 = gr.Button("📚 Story", size="sm")
                
                with gr.Row():
                    tts_example_btn4 = gr.Button("🎵 Song Lyrics", size="sm")
                    tts_example_btn5 = gr.Button("📖 Poem", size="sm")
                    tts_example_btn6 = gr.Button("💼 Business", size="sm")
                
                with gr.Row():
                    tts_example_btn7 = gr.Button("🎭 Drama", size="sm")
                    tts_example_btn8 = gr.Button("🔔 Notification", size="sm")
                
                accent = gr.Textbox(
                    label="Voice Accent (Optional)",
                    placeholder="e.g., en-US-female-27, en-GB-male-2",
                    info="Default voice is used if left blank. Ignored if Voice Clone ID is provided."
                )
                
                voice_clone_id = gr.Textbox(
                    label="Voice Clone ID (Optional)",
                    placeholder="Enter a voice clone ID to use a custom voice.",
                    info="Overrides the accent if provided."
                )

            with gr.Column():
                gr.Markdown("#### Generated Audio")
                audio_output = gr.Audio(label="Speech Output")
                tts_status = gr.Textbox(label="Status", interactive=False, placeholder="Ready to generate speech...")

    tts_btn = gr.Button("Generate Speech", variant="primary")

    # Example functions to auto-fill text field
    def fill_tts_example_1():
        return "Hello! Welcome to our AI-powered text-to-speech system. This technology can convert any written text into natural-sounding speech."
    
    def fill_tts_example_2():
        return "Attention all passengers. Flight 1234 to New York is now boarding at gate 15. Please have your boarding pass ready."
    
    def fill_tts_example_3():
        return "Once upon a time, in a magical forest, there lived a wise old owl who loved to share stories with all the woodland creatures."
    
    def fill_tts_example_4():
        return "Twinkle twinkle little star, how I wonder what you are. Up above the world so high, like a diamond in the sky."
    
    def fill_tts_example_5():
        return "The road not taken by Robert Frost. Two roads diverged in a yellow wood, and sorry I could not travel both."
    
    def fill_tts_example_6():
        return "Thank you for your business. Your order has been confirmed and will be shipped within 2-3 business days."
    
    def fill_tts_example_7():
        return "To be or not to be, that is the question. Whether tis nobler in the mind to suffer the slings and arrows of outrageous fortune."
    
    def fill_tts_example_8():
        return "You have a new message. Please check your inbox for important updates regarding your account."

    # Connect example buttons to auto-fill functions
    tts_example_btn1.click(fill_tts_example_1, outputs=[tts_text])
    tts_example_btn2.click(fill_tts_example_2, outputs=[tts_text])
    tts_example_btn3.click(fill_tts_example_3, outputs=[tts_text])
    tts_example_btn4.click(fill_tts_example_4, outputs=[tts_text])
    tts_example_btn5.click(fill_tts_example_5, outputs=[tts_text])
    tts_example_btn6.click(fill_tts_example_6, outputs=[tts_text])
    tts_example_btn7.click(fill_tts_example_7, outputs=[tts_text])
    tts_example_btn8.click(fill_tts_example_8, outputs=[tts_text])

    tts_btn.click(
        text_to_speech,
        inputs=[tts_text, accent, voice_clone_id],
        outputs=[audio_output, tts_status]
    )



demo.launch()