Duolingo scales DuoRadio from 300 to 15,000+ episodes with generative AI, growing daily sessions 10x in fewer than 6 months
DuoRadio's reach was constrained by a labor-intensive manual production process: crafting 300 episodes for a handful of courses took nearly a year, requiring meticulous scripting, voice actors, and specialized audio editing, leaving only a small percentage of learners with access to the feature.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Curriculum content input
Existing learning curriculum content is fed to the generative AI model, providing specific patterns to follow.
DuoRadio daily sessions grew from 500K to 5M in fewer than 6 months; total episodes expanded from 300 to 15,000+ and courses from 2 to 25+ in fewer than two quarters — a task that would otherwise have taken 5+ years — while saving 99% of costs.
What failed first
Two early generative AI attempts both failed: generating original scripts from scratch produced subpar results requiring extensive manual editing, and automated translation of existing English episodes frequently missed translation accuracy and proficiency level targets, again leading to time-consuming revisions.