--- title: Audio Stories emoji: 🌍 colorFrom: yellow colorTo: gray sdk: gradio sdk_version: 5.18.0 app_file: app.py pinned: false --- Here's a refined version of your text with improved clarity and flow: --- Here's a refined version of your text with improved clarity and flow: --- Here's a refined version of your text with improved clarity and flow: --- ### **Storytelling Text-to-Speech (TTS) Application** #### **Project Objectives** This project aims to develop an interactive Text-to-Speech (TTS) application that enables users to input stories and have them narrated using diverse voices in multiple languages. #### **Implemented Pipelines** The application leverages the Edge TTS service for high-quality voice synthesis, offering a range of neural voices across different languages. Key functionalities include: - **Text Input:** Users can enter the story they wish to convert into speech. - **Language Selection:** A dropdown menu allows users to choose from various languages, including English and Arabic. - **Speaker Selection:** Based on the selected language, users can pick from a list of available speakers. - **Audio Generation:** Clicking the “Generate Magical Audio” button processes the text and produces an audio file. - **Audio Playback:** The generated audio file is displayed, allowing users to listen to the narration. #### **How to Use the Interface** 1. **Enter Your Story:** Type your text into the provided input field. 2. **Select Language:** Choose your preferred language from the dropdown menu. 3. **Pick a Speaker:** Select a speaker corresponding to the chosen language. 4. **Generate Audio:** Click the "Generate Magical Audio" button to create the narration. 5. **Listen to the Output:** Once generated, the audio file will be available for playback. #### **Justification for Model and Pipeline Choices** - **Edge TTS Service:** Chosen for its advanced neural voice synthesis, Edge TTS delivers natural-sounding speech and supports multiple languages, enhancing the storytelling experience. - **User-Friendly Interface:** The application is built using Gradio, ensuring an intuitive and interactive user experience for seamless text-to-speech conversion.