Elevenlabs Extension Improvement and migration to official API (#1830)

extensions/elevenlabs_tts/requirements.txt

@@ -1,3 +1 @@
-elevenlabslib
+elevenlabs==0.2.*
-soundfile
-sounddevice

extensions/elevenlabs_tts/script.py

@@ -2,51 +2,55 @@ import re
 from pathlib import Path
 
 import gradio as gr
-from elevenlabslib import ElevenLabsUser
+import elevenlabs
-from elevenlabslib.helpers import save_bytes_to_path
 
-import modules.shared as shared
+from modules import chat, shared
+from modules.html_generator import chat_html_wrapper
 
 params = {
     'activate': True,
-    'api_key': '12345',
+    'api_key': None,
     'selected_voice': 'None',
+    'autoplay': False,
+    'show_text': True,
 }
 
-initial_voice = ['None']
+voices = None
 wav_idx = 0
-user = ElevenLabsUser(params['api_key'])
-user_info = None
-
-# Check if the API is valid and refresh the UI accordingly.
-def check_valid_api():
-    global user, user_info, params
-
-    user = ElevenLabsUser(params['api_key'])
-    user_info = user._get_subscription_data()
-    print('checking api')
-    if not params['activate']:
-        return gr.update(value='Disconnected')
-    elif user_info is None:
-        print('Incorrect API Key')
-        return gr.update(value='Disconnected')
-    else:
-        print('Got an API Key!')
-        return gr.update(value='Connected')
 
 
-# Once the API is verified, get the available voices and update the dropdown list
 def refresh_voices():
+    global params
+    your_voices = elevenlabs.voices(api_key=params['api_key'])
+    voice_names = [voice.name for voice in your_voices]
+    return voice_names
 
-    global user, user_info
 
-    your_voices = [None]
+def refresh_voices_dd():
-    if user_info is not None:
+    all_voices = refresh_voices()
-        for voice in user.get_available_voices():
+    return gr.Dropdown.update(value=all_voices[0], choices=all_voices)
-            your_voices.append(voice.initialName)
+
-        return gr.Dropdown.update(choices=your_voices)
+
-    else:
+def remove_tts_from_history(name1, name2, mode):
-        return
+    for i, entry in enumerate(shared.history['internal']):
+        shared.history['visible'][i] = [shared.history['visible'][i][0], entry[1]]
+    return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
+
+
+def toggle_text_in_history(name1, name2, mode):
+    for i, entry in enumerate(shared.history['visible']):
+        visible_reply = entry[1]
+        if visible_reply.startswith('<audio'):
+            if params['show_text']:
+                reply = shared.history['internal'][i][1]
+                shared.history['visible'][i] = [
+                    shared.history['visible'][i][0], f"{visible_reply.split('</audio>')[0]}</audio>\n\n{reply}"
+                ]
+            else:
+                shared.history['visible'][i] = [
+                    shared.history['visible'][i][0], f"{visible_reply.split('</audio>')[0]}</audio>"
+                ]
+    return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
 
 
 def remove_surrounded_chars(string):
@@ -65,7 +69,14 @@ def input_modifier(string):
     This function is applied to your text inputs before
     they are fed into the model.
     """
-
+    # Remove autoplay from the last reply
+    if shared.is_chat() and len(shared.history['internal']) > 0:
+        shared.history['visible'][-1] = [
+            shared.history['visible'][-1][0],
+            shared.history['visible'][-1][1].replace('controls autoplay>', 'controls>')
+        ]
+    if params['activate']:
+        shared.processing_message = "*Is recording a voice message...*"
     return string
 
 
@@ -74,13 +85,12 @@ def output_modifier(string):
     This function is applied to the model outputs.
     """
 
-    global params, wav_idx, user, user_info
+    global params, wav_idx
 
     if not params['activate']:
         return string
-    elif user_info is None:
-        return string
 
+    original_string = string
     string = remove_surrounded_chars(string)
     string = string.replace('"', '')
     string = string.replace('“', '')
@@ -90,31 +100,78 @@ def output_modifier(string):
     if string == '':
         string = 'empty reply, try regenerating'
 
-    output_file = Path(f'extensions/elevenlabs_tts/outputs/{wav_idx:06d}.wav'.format(wav_idx))
+    output_file = Path(f'extensions/elevenlabs_tts/outputs/{wav_idx:06d}.mp3'.format(wav_idx))
-    voice = user.get_voices_by_name(params['selected_voice'])[0]
+    print(f'Outputing audio to {str(output_file)}')
-    audio_data = voice.generate_audio_bytes(string)
+    try:
-    save_bytes_to_path(Path(f'extensions/elevenlabs_tts/outputs/{wav_idx:06d}.wav'), audio_data)
+        audio = elevenlabs.generate(text=string, voice=params['selected_voice'], model="eleven_monolingual_v1")
+        elevenlabs.save(audio, str(output_file))
 
-    string = f'<audio src="file/{output_file.as_posix()}" controls></audio>'
+        autoplay = 'autoplay' if params['autoplay'] else ''
-    wav_idx += 1
+        string = f'<audio src="file/{output_file.as_posix()}" controls {autoplay}></audio>'
+        wav_idx += 1
+    except elevenlabs.api.error.UnauthenticatedRateLimitError:
+        string = "🤖 ElevenLabs Unauthenticated Rate Limit Reached - Please create an API key to continue\n\n"
+    except elevenlabs.api.error.RateLimitError:
+        string = "🤖 ElevenLabs API Tier Limit Reached\n\n"
+    except elevenlabs.api.error.APIError as err:
+        string = f"🤖 ElevenLabs Error: {err}\n\n"
+
+    if params['show_text']:
+        string += f'\n\n{original_string}'
+
+    shared.processing_message = "*Is typing...*"
     return string
 
 
 def ui():
-
+    global voices
+    if not voices:
+        voices = refresh_voices()
+        params['selected_voice'] = voices[0]
     # Gradio elements
     with gr.Row():
         activate = gr.Checkbox(value=params['activate'], label='Activate TTS')
-        connection_status = gr.Textbox(value='Disconnected', label='Connection Status')
+        autoplay = gr.Checkbox(value=params['autoplay'], label='Play TTS automatically')
-
+        show_text = gr.Checkbox(value=params['show_text'], label='Show message text under audio player')
-    voice = gr.Dropdown(value=params['selected_voice'], choices=initial_voice, label='TTS Voice')
+    with gr.Row():
+        voice = gr.Dropdown(value=params['selected_voice'], choices=voices, label='TTS Voice')
+        refresh = gr.Button(value='Refresh')
     with gr.Row():
         api_key = gr.Textbox(placeholder="Enter your API key.", label='API Key')
-        connect = gr.Button(value='Connect')
+    with gr.Row():
+        convert = gr.Button('Permanently replace audios with the message texts')
+        convert_cancel = gr.Button('Cancel', visible=False)
+        convert_confirm = gr.Button('Confirm (cannot be undone)', variant="stop", visible=False)
 
+    # Convert history with confirmation
+    convert_arr = [convert_confirm, convert, convert_cancel]
+    convert.click(
+        lambda: [gr.update(visible=True), gr.update(visible=False),
+                 gr.update(visible=True)], None, convert_arr
+    )
+    convert_confirm.click(
+        lambda: [gr.update(visible=False), gr.update(visible=True),
+                 gr.update(visible=False)], None, convert_arr
+    )
+    convert_confirm.click(
+        remove_tts_from_history, [shared.gradio[k] for k in ['name1', 'name2', 'mode']], shared.gradio['display']
+    )
+    convert_confirm.click(lambda: chat.save_history(timestamp=False), [], [], show_progress=False)
+    convert_cancel.click(
+        lambda: [gr.update(visible=False), gr.update(visible=True),
+                 gr.update(visible=False)], None, convert_arr
+    )
     # Event functions to update the parameters in the backend
     activate.change(lambda x: params.update({'activate': x}), activate, None)
     voice.change(lambda x: params.update({'selected_voice': x}), voice, None)
     api_key.change(lambda x: params.update({'api_key': x}), api_key, None)
-    connect.click(check_valid_api, [], connection_status)
+    # connect.click(check_valid_api, [], connection_status)
-    connect.click(refresh_voices, [], voice)
+    refresh.click(refresh_voices_dd, [], voice)
+    # Toggle message text in history
+    show_text.change(lambda x: params.update({"show_text": x}), show_text, None)
+    show_text.change(
+        toggle_text_in_history, [shared.gradio[k] for k in ['name1', 'name2', 'mode']], shared.gradio['display']
+    )
+    show_text.change(lambda: chat.save_history(timestamp=False), [], [], show_progress=False)
+    # Event functions to update the parameters in the backend
+    autoplay.change(lambda x: params.update({"autoplay": x}), autoplay, None)