streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
Why it matters
Real-time transcription now has a first-class streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → API in the AI SDK: pipe raw PCM chunks over a socket and get a transcript that updates mid-recording, without wiring a provider SDK yourself.
