Spaces:
Sleeping
Sleeping
| import os | |
| import streamlit as st | |
| from huggingface_hub import InferenceApi | |
| from dotenv import load_dotenv | |
| import base64 | |
| import requests | |
| # Load environment variables from the .env file | |
| load_dotenv() | |
| # Set your Hugging Face API token from the environment variable | |
| HUGGINGFACE_API_TOKEN = os.getenv("HUGGINGFACE_API_TOKEN") | |
| # Function to get user input | |
| def get_text(): | |
| input_text = st.text_input("Enter text for speech generation:", key="input") | |
| return input_text | |
| # Function to select the language model | |
| def select_language(): | |
| language_options = { | |
| "English": "google/tts_model_en", | |
| "Spanish": "google/tts_model_es", | |
| "German": "google/tts_model_de", | |
| "French": "google/tts_model_fr", | |
| "Italian": "google/tts_model_it", | |
| } | |
| selected_language = st.selectbox("Select Language", list(language_options.keys())) | |
| return language_options[selected_language] | |
| # Initialize Streamlit UI | |
| st.set_page_config(page_title="Multilingual Text-to-Speech", page_icon="🔊") | |
| st.header("Multilingual Text-to-Speech Demo") | |
| # Get user input and language selection | |
| user_input = get_text() | |
| model_id = select_language() | |
| # Function to play audio in Streamlit | |
| def play_audio(audio_bytes): | |
| b64 = base64.b64encode(audio_bytes).decode() | |
| audio_html = f""" | |
| <audio controls autoplay> | |
| <source src="data:audio/wav;base64,{b64}" type="audio/wav"> | |
| Your browser does not support the audio element. | |
| </audio> | |
| """ | |
| st.markdown(audio_html, unsafe_allow_html=True) | |
| # Create a button for generating speech | |
| submit = st.button('Generate Speech') | |
| # If the generate button is clicked and user input is not empty | |
| if submit and user_input: | |
| with st.spinner("Generating speech..."): | |
| # Make a direct request to the API | |
| url = f"https://api-inference.huggingface.co/models/{model_id}" | |
| headers = {"Authorization": f"Bearer {HUGGINGFACE_API_TOKEN}"} | |
| payload = {"inputs": user_input} | |
| # Requesting raw response with the option to manually handle the audio | |
| response = requests.post(url, headers=headers, json=payload, stream=True) | |
| if response.status_code == 200: | |
| audio_data = response.content | |
| # Assuming the response is in audio/wav or another format | |
| play_audio(audio_data) | |
| else: | |
| st.error(f"Error: {response.status_code} - {response.text}") | |
| elif submit: | |
| st.warning("Please enter some text.") # Warning for empty input | |
| has context menu |