Notes & essays

All Posts

Technical writing on conversational AI, speech, language models, and the things I build.

Jul 5, 20268 min read

react-native-tts-kit: On-Device Neural TTS in Three Lines

We built on-device neural text-to-speech for Flowent because React Native had no good answer — 31 languages, no API keys, no network calls, no per-request bill. Now it is open source. Here is the path from install to shipping, rough edges included.

react-nativeexpottson-deviceopen-source

Jun 22, 20262 min read

Flowent Is Live on the App Store and Google Play

Flowent — the real-time voice agent for language immersion — is now available to download on iOS and Android.

flowentvoice-agentlanguage-learninglaunch

May 17, 20267 min read

Reading Emotion From a Silent Face: Gemini 3 Flash vs Qwen2.5-VL-32B

Two vision-language models, the same 150 silent RAVDESS clips, one question — can a VLM read emotion from a face with the audio stripped out? A head-to-head on classification accuracy and per-class behaviour.

vlmemotion-recognitionravdessevaluationbenchmark