text-generation-webui/extensions/silero_tts/script.py

import asyncio
from pathlib import Path

import gradio as gr
import torch
import io
import json
import os

import requests

from elevenlabslib.helpers import *
from elevenlabslib import *

params = {
    'activate': True,
    'api_key': '12345',
    'selected_voice': 'None',
}
initial_voice = ['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 params['activate'] == False:
        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 user, user_info
    
    your_voices = [None]
    if user_info is not None:
        for voice in user.get_available_voices():
            your_voices.append(voice.initialName)
        return  gr.Dropdown.update(choices=your_voices)
    else:
        return

def remove_surrounded_chars(string):
    new_string = ""
    in_star = False
    for char in string:
        if char == '*':
            in_star = not in_star
        elif not in_star:
            new_string += char
    return new_string

def input_modifier(string):
    """
    This function is applied to your text inputs before
    they are fed into the model.
    """

    return string

def output_modifier(string):
    """
    This function is applied to the model outputs.
    """
    global params, wav_idx, user, user_info
    
    if params['activate'] == False:
        return string
    elif user_info == None:
        return string

    string = remove_surrounded_chars(string)
    string = string.replace('"', '')
    string = string.replace('“', '')
    string = string.replace('\n', ' ')
    string = string.strip()

    if string == '':
        string = 'empty reply, try regenerating'
        
    output_file = Path('extensions/elevenlabs_tts/outputs/{}.wav'.format(wav_idx))
    voice = user.get_voices_by_name(params['selected_voice'])[0]
    audio_data = voice.generate_audio_bytes(string)
    save_bytes_to_path("extensions/elevenlabs_tts/outputs/{}.wav".format(wav_idx), audio_data)


    string = f'<audio src="file/{output_file.as_posix()}" controls></audio>'
    wav_idx += 1
    return string


def ui():
    # Gradio elements
    with gr.Row():
        activate = gr.Checkbox(value=params['activate'], label='Activate TTS')
        connection_status = gr.Textbox(value='Disconnected', label='Connection Status')
    voice = gr.Dropdown(value=params['selected_voice'], choices=initial_voice, label='TTS Voice')
    with gr.Row():
        api_key = gr.Textbox(placeholder="Enter your API key.", label='API Key')
        connect = gr.Button(value='Connect')
    # 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(refresh_voices, [], voice)