App
lllanguage
A language practice app that saves vocabulary from conversations for later review.

When you need a word during a conversation, it is easy to forget to look it up afterwards. I am building lllanguage to capture those moments.
The app combines spoken practice with vocabulary review, using words from your conversations. It is still in development.
Built with
Expo / React Native (audio streaming) · Fastify + WebSocket server · PostgreSQL · Local ASR / TTS / Ollama adapters · Next.js marketing + store pages
Technical challenges
- 01
Continuous PCM over WebSocket from a mobile client that cannot stream raw frames through Expo's stock recorder.
- 02
Realtime speak path: partial ASR, adaptive endpointing, barge-in, and stripping partner TTS echo from the learner's transcript.
- 03
Keeping lesson state and conversation rules in a deterministic reducer, with the LLM proposing actions for the reducer to validate.
- 04
Running speech and language models locally in Docker to test without hosted inference costs.
Role
I designed, built, and released it.