Voice in.
Voice out.
Three shapes of voice-first interfaces — a single full-duplex speech-to-speech model, a compositional wake → VAD → ASR → LLM → TTS pipeline you fully control, and wake-word activation for hands-free entry. All on-device, no cloud APIs, no audio leaving the device.
Studio tạo giọng. Runner trò chuyện bằng giọng đó.
Speech Studio và Runner là hai mặt của cùng một ngăn xếp giọng nói cục bộ: một cho sản xuất giọng nói, một cho tương tác tác nhân giọng nói trực tiếp.
Pick the shape that fits your product.
Drop-in dialogue model, compositional pipeline with per-stage control, or a thin wake-word trigger. Each runs entirely on-device.
A single model takes mic input and produces voice output. Drop-in OpenAI-Realtime-compatible WebSocket; minimal code, opaque internals.
Wake-word → VAD → streaming ASR → on-device LLM → TTS. Per-stage control, transcript visibility, swap engines freely. Build your own Siri.
Hands-free trigger for any voice flow. Custom keywords with per-phrase thresholds, sub-5 MB on-device, 26× real-time.