main.py

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


load_dotenv()
KEY_ELEVENLABS = os.getenv('ELEVENLABS_KEY')
print(KEY_ELEVENLABS)


def generate_audio(text_input: str, creator: str) -> str:
    CHUNK_SIZE = 1024

    headers = {
        "Accept": "application/json",
        "xi-api-key": KEY_ELEVENLABS
    }

    voice_id = ''

    match creator:
        case 'Roomie':
            voice_id = '2Onew6n5JwT9uEbmTSrO'
        case 'Xavy':
            voice_id = 'cYBsY94mzMC7VpGoVMgr'
        case 'Bella':
            voice_id = 'X9j5sAaRD6aEgBblOUOG'

    url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream"

    payload = {
        "text": text_input,
        "model_id": "eleven_monolingual_v1",
        "voice_settings": {
            "stability": 0.5,
            "similarity_boost": 0.8,
            "style": 0.0,
            "use_speaker_boost": False
        }
    }

    response = requests.post(url, headers=headers, json=payload, stream=True)
    print(response)
    with open('output.wav', 'wb') as f:
        for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
            if chunk:
                f.write(chunk)

    return f'{pathlib.Path().resolve()}\output.mp3'


app = gr.Interface(
    fn=generate_audio,
    inputs=[gr.Textbox(label='Text to Speach'), gr.Dropdown(
        ['Roomie', 'Xavy', 'Bella'], label="Coice your creator")],
    outputs=['audio']
)

app.launch()