Checked fact 5224 Oct 2026Models and releases
The post says it "produces its first hypotheses (known as “partials”) in just over 100ms of receiving audio."
The exact words it rests on
it produces its first hypotheses (known as “partials”) in just over 100ms of receiving audio.
What the source said when we opened it, on 4 Oct 2026.
The source
Our first streaming transcription model debuts at no. 1 on Artificial Analysis
Checked
Checked by the notis newsroom on , against the source above.
In the story
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.