Pronunciation
Dictionary
A pronunciation-focused dictionary tool that teaches through music and serves as an SEO entry point into Letras Academy.
Once Letras Academy existed, an idea came up in our idea bank: tap into the programmatic-SEO potential of dictionaries (thousands of indexable pages) and the behavior of people who were already learning a language through Letras translations and arrived wanting a specific word, its translation and, above all, its pronunciation.
That's how the Pronunciation Dictionary was born, in 2021. With the team buried in other projects, I designed the feature on my own.
Deliver something that felt like a dictionary, focused on a word and its translations, but that went beyond the ordinary one: actually teach, and teach through music, which is what makes Letras unique. All of it on a template that had to exist at programmatic scale, thousands of words, to capture long-tail search without each page turning into thin content.
What sets this page apart from any dictionary is seeing the word used in song excerpts and being able to hear each one.
That came from a data asset we already had, the subtitle database, which stores the exact timestamp of each word in a song. Whenever we could use proprietary data, we did: it's more reliable and it's our brand.
Beyond the song excerpts, the page offers:
- pronunciation in several English accents;
- variations and synonyms;
- the word used in example sentences, with audio.
Scale without giving up quality
The content that didn't come from our own data came from generative AI, back in 2021, at the start of all this. I built a generation pipeline, tested different providers and models, and ran a few rounds of curation to refine the prompt before generating at scale.
The rule was simple: there's no quantity without real quality. In a pronunciation dictionary, one wrong piece of information breaks trust, so curation came before scale, never after.
At its peak, the dictionary passed 30,000 visits a day, and it wasn't idle traffic: more than half converted to Letras Academy's offers, fulfilling the top-of-funnel SEO role that motivated the project. It's still live. It was also an early, concrete lesson in generating content at scale with AI without giving up quality, when that was still new.