inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
Removes the free-tier paywall that blocks cheap prototyping of voice agents and TTS pipelines, and the underlying GPU kernel work is a concrete example of inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → optimization making a frontier voice model free to run at scale.
