Update app.py

app.py

@@ -7,7 +7,9 @@ import uuid
 from elevenlabs import VoiceSettings
 from elevenlabs.client import ElevenLabs
 from pathlib import Path
-
+from scipy.io.wavfile import write
+from scipy.io.wavfile import read
+import yt_dlp
 
 ELEVENLABS_API = os.environ.get("ELEVENLABS_API")
 
@@ -71,6 +73,28 @@ def text_to_speech(text):
 
     return save_file_path
 
+
+
+def download_audio(url):
+    ydl_opts = {
+        'format': 'bestaudio/best',
+        'outtmpl': 'ytdl/%(title)s.%(ext)s',
+        'postprocessors': [{
+            'key': 'FFmpegExtractAudio',
+            'preferredcodec': 'wav',
+            'preferredquality': '192',
+        }],
+    }
+
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        info_dict = ydl.extract_info(url, download=True)
+        file_path = ydl.prepare_filename(info_dict).rsplit('.', 1)[0] + '.wav'
+        sample_rate, audio_data = read(file_path)
+        audio_array = np.asarray(audio_data, dtype=np.int16)
+
+        return sample_rate, audio_array
+
+
 with gr.Blocks() as demo:
     gr.Markdown("## audio Translator")
     gr.Markdown(
@@ -83,6 +107,18 @@ with gr.Blocks() as demo:
         """
     )
     audio_input = gr.Audio(type="filepath", show_download_button=True)
+    with gr.Accordion("inputs by Link", open = False):
+        with gr.Row():
+            link = gr.Textbox(
+                label = "Link",
+                placeholder = "Paste the link here",
+                interactive = True
+            )
+            download_button = gr.Button(
+                "Download!",
+                variant = "primary"
+            )
+            download_button.click(download_audio, [link], [audio_input])
     submit = gr.Button("Submit", variant="primary")
     clear_button = gr.ClearButton(audio_input, "Clear")