SUN Web & API

Overview

SUN is an artificial intelligence audio generation platform designed to transform text prompts, documents, and media notes into conversational podcasts, audiobooks, and structured audio courses. Developed for web and mobile interfaces with developer API availability, the system researches, plans, scripts, and voices audio content across single or dual-host formats. It supports multiple synthetic speech models to automate the production of educational and narrative spoken audio.

Key Features

• Multi-format source ingestion — The platform generates episodes directly from text prompts, pasted notes, YouTube video transcripts, and uploaded documents such as PDFs and slide decks.
• Multi-speaker script writing — The engine plans and writes conversational dialogue between two synthetic hosts or formats single-narrator scripts for book readings and sequential lessons.
• Multilingual voice library and cloning — Users can choose from narrators speaking English, Spanish, Hindi, and Chinese, or clone their own voice for private account use with one minute of recorded sample audio.
• Structured audio course creation — The system organizes broad subjects into multi-lesson audio courses with sequential chapters, contextual explanations, and post-lesson exercises.
• Automated publication scheduling — An internal scheduler automatically creates and delivers fresh episodes on fixed daily or weekly cadences without manual prompting.
• In-progress stream playback — Using processing models such as Genesis Vega, audio begins streaming for listeners while the remainder of the episode is actively generating.

Who It's For

SUN is designed for individual learners, educators, and corporate training teams who need to transform written reference materials, lecture notes, and documentation into accessible audio formats. It is also built for authors seeking rapid audiobook production and developers looking to programmatically integrate conversational audio generation into their products.

Notable Strengths

Unlike standard text-to-speech engines that perform direct reading, SUN structures, researches, and scripts multi-character educational discussions tailored to user-specified comprehension levels. Its processing pipeline enables rapid generation—benchmarked at approximately 24 seconds per audio minute—alongside progressive streaming during rendering. Additionally, the service provides an accessible entry model with an initial free generation hour followed by non-expiring pay-as-you-go audio credits.