Text-to-Speech (TTS)
Synthesize natural, streaming speech waveforms directly on-device in React Native using multi-stage neural pipelines (Supertonic and Kokoro).
Speech-to-Text (STT)
Transcribe spoken audio in real time on-device in React Native using OpenAI Whisper with integrated Voice Activity Detection.
Voice Activity Detection (VAD)
Detect speech vs silence intervals in real time on-device in React Native using lightweight neural FSMN-VAD.