Noise reduction, voice activity detection, streaming speech-to-text, turn control, the model and streaming synthesis, running as one pipeline over telephony or from the browser.
One pipeline serves both, with zero code forks.
One runtime underneath all of it. The engine is what the platform runs on; the models are the layers it owns, arriving on their own as they are ready.
A real-time voice engine where everything streams end to end: streaming speech-to-text, turn control, the hallucination gate, barge-in classification, multimodal intent understanding and streaming synthesis.
Context-aware linear streaming transcription: full-context transcription at linear cost, any turn length.
Natively streaming synthesis, per sentence, in a voice taken from one reference sample.
Drop in your website and Alebex reads it, learns what you do, and calls you in under 30 seconds.