Story

Overview

Story is a command-line tool that generates AI-driven narratives and turns them into illustrated, narrated content. It runs as a generation pipeline: an AI model writes the story text, Fal.ai synthesises accompanying images, and ElevenLabs and Google Cloud Text-to-Speech produce the voiceover audio.

Key Features

• AI Narrative Generation: Generates story text using Google Generative AI
• Image Synthesis: Produces illustrations for the story via Fal.ai
• Voiceover Audio: Synthesises narration audio using ElevenLabs and Google Cloud Text-to-Speech
• CLI Pipeline: Runs as a command-line tool that chains text, image, and audio generation
• Composable Output: Combines generated text, images, and audio into a single storytelling output

Technical Stack

• Language: TypeScript on Node.js
• Text Generation: Google Generative AI
• Image Generation: Fal.ai
• Audio / TTS: ElevenLabs, Google Cloud Text-to-Speech

Architecture

The project is a CLI generation pipeline rather than a web application:

• Text Stage: Google Generative AI produces the story narrative
• Image Stage: Fal.ai synthesises images from prompts derived from the narrative
• Audio Stage: ElevenLabs and Google Cloud Text-to-Speech generate the voiceover
• Orchestration: A Node.js / TypeScript CLI coordinates the stages and writes the output assets

Challenges & Solutions

• Multi-Service Orchestration: Coordinated several AI services (text, image, audio) into one pipeline
• Media Synthesis: Integrated Fal.ai image generation and TTS voiceover into a single workflow
• CLI Ergonomics: Built the tool to run end-to-end from the command line

Impact & Results

• Automated Storytelling: Turns a prompt into an illustrated, narrated story without manual media work
• AI Exploration: Demonstrates combining text, image, and audio generation services