app.py

import pathlib
import yt_dlp
import uuid
import os
import gradio as gr
from tqdm import tqdm


def transcribe_video(d_id_key: str, elv_key: str, full_text: str):
    print("Test")
    segments="Work In Progress"
       
    return segments


demo = gr.Interface(fn=transcribe_video, inputs=[
    gr.Textbox(label="D-Id API Key",placeholder="Paste your D-Id",type='password'),
    gr.Textbox(label="Elevenlabs API Keys",placeholder="Paste Elevenlabs",type='password'),
    gr.Textbox(lines=4, label=" Please input the text you wish to generate in order to make the photo speak.", placeholder="English Text here"),
    gr.Image(label="Upload a photo of a face here, and generate a talking animation.", type="pil")
  ], outputs="text",title="Bring your images to life with the talking animation feature now!")

demo.launch()