A Gemini AI Studio-powered utility for converting plain text into Speech Markdown Language (SML) with AI-inferred emotion and prosody.

This application uses Google's Gemini AI to automatically analyze text and generate Speech Markdown with appropriate prosodic elements including:

• Emotional tone inference
• Prosody markers (pitch, rate, volume)
• Natural speech patterns
• SSML-compatible output

• Drag & Drop Upload: Simple file upload interface for TXT or MD files
• AI-Powered Analysis: Gemini AI automatically infers emotional context and appropriate prosody
• Batch Processing: Handle entire books or long-form content
• Real-time Generation: See progress as your text is processed

Prerequisites: Node.js

1. Clone this repository:

   git clone https://github.com/danielrosehill/Text-To-SSML-Generator.git
   cd Text-To-SSML-Generator

2. Install dependencies:

   npm install

3. Set up your Gemini API key:

   • Copy .env.local.example to .env.local (if needed)
   • Add your Gemini API key:

     GEMINI_API_KEY=your_api_key_here
     

4. Run the development server:

   npm run dev

5. Open your browser and navigate to http://localhost:3000 (or the port shown in terminal)

1. Click the upload area or drag and drop your TXT or MD file
2. Click "Generate SML" to start the conversion
3. Wait for the AI to process your text
4. Download or copy the generated Speech Markdown

1. Visit Google AI Studio
2. Sign in with your Google account
3. Navigate to "Get API Key"
4. Create a new API key or use an existing one

• Audiobook Production: Add natural prosody to book narrations
• Voice Assistant Development: Create more expressive TTS output
• Content Accessibility: Enhance screen reader experiences
• Podcast Scripts: Add emotional markers to scripted content

• Built with Gemini AI Studio
• Node.js runtime
• Speech Markdown Language (SML) output format

Contributions welcome! Please feel free to submit issues or pull requests.

Prompt and idea: me (Daniel Rosehill)

Code: Gemini Pro 2.5 via AI Studio app builder

• AI Studio App
• Speech Markdown Specification