# app.py
# Gradio TTS demo using GroqCloud / PlayAI TTS via the OpenAI-compatible Groq endpoint

import os
import tempfile
import requests
import gradio as gr
from dotenv import load_dotenv

# Load .env for local use (Hugging Face Spaces ignores if not present)
load_dotenv()

# --- Configuration ---
GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
GROQ_TTS_ENDPOINT = "https://api.groq.com/openai/v1/audio/speech"
DEFAULT_MODEL = "playai-tts"

EXAMPLE_VOICES = [
    "Fritz-PlayAI",
    "Emma-PlayAI",
    "Alloy-PlayAI",
]


def synthesize_text(text: str, voice: str = None, model: str = DEFAULT_MODEL, response_format: str = "wav"):
    """Call Groq TTS and return path to temporary audio file."""
    if not GROQ_API_KEY:
        return None, "Missing GROQ_API_KEY environment variable. Add it in your Hugging Face Space Secrets."

    if not text or text.strip() == "":
        return None, "Please provide some text to synthesize."

    payload = {
        "model": model,
        "input": text,
        "response_format": response_format,
    }
    if voice:
        payload["voice"] = voice

    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {GROQ_API_KEY}",
    }

    try:
        resp = requests.post(GROQ_TTS_ENDPOINT, json=payload, headers=headers, stream=True, timeout=60)
    except Exception as e:
        return None, f"Request failed: {e}"

    if resp.status_code != 200:
        try:
            detail = resp.json()
        except Exception:
            detail = resp.text
        return None, f"Groq API error ({resp.status_code}): {detail}"

    suffix = ".wav" if response_format == "wav" else ".mp3"
    tmp = tempfile.NamedTemporaryFile(delete=False, suffix=suffix)
    for chunk in resp.iter_content(chunk_size=8192):
        if chunk:
            tmp.write(chunk)
    tmp.flush()
    tmp.close()

    return tmp.name, "Synthesis successful!"


with gr.Blocks(title="GroqCloud TTS — Hugging Face Space") as demo:
    gr.Markdown("# 🎙️ GroqCloud Text-to-Speech\nConvert your text to natural speech using Groq TTS API.")

    with gr.Row():
        with gr.Column(scale=3):
            txt = gr.Textbox(lines=6, label="Text", placeholder="Enter text here...")
            voice = gr.Dropdown(EXAMPLE_VOICES, label="Voice", value=EXAMPLE_VOICES[0])
            resp_format = gr.Radio(["wav", "mp3"], value="wav", label="Output format")
            synth_btn = gr.Button("🔊 Synthesize")
            status = gr.Textbox(label="Status", interactive=False)

        with gr.Column(scale=2):
            audio_out = gr.Audio(label="Generated Audio", type="filepath")

    def on_synthesize(text, voice, response_format):
        path, msg = synthesize_text(text, voice, DEFAULT_MODEL, response_format)
        return path, msg

    synth_btn.click(on_synthesize, inputs=[txt, voice, resp_format], outputs=[audio_out, status])

# ✅ Important: launch the app!
if __name__ == "__main__":
    demo.launch()