TTS Studio

What it does

Our app leverages the Gemini API to generate customized stories based on user input. Here's how we use it:

Story Suggestions: When a user selects a genre, the app queries the Gemini API to fetch relevant story suggestions. We provide the API with a prompt specifying the genre and request a list of potential story types.

Story Generation: Once a user selects a story type, the app sends a request to the Gemini API to generate the complete story. The prompt includes details about the chosen genre and story type, ensuring that the generated content is aligned with user preferences.

Content Formatting: The API returns the story in a JSON format. We then process this JSON response to extract the story title and content. The story is formatted into paragraphs with appropriate punctuation to enhance readability and facilitate text-to-speech (TTS) functionality.

Error Handling and Duplication Prevention: We handle potential errors and ensure that the generated content is unique. If the API response contains errors or duplicates, we retry the request or fetch new suggestions to provide fresh and engaging content.

The Gemini API's advanced language model enables us to offer a diverse range of stories, ensuring that users receive creative and unique narratives every time they interact with our app.