Fact · Speech recognition
OpenAI's speech-to-text guide says that file streaming is supported by its gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize models, and that the whisper-1 model does not support it.
Checked against its source on October 17, 2026
In the source's own words
“Existing gpt-4o-transcribe , gpt-4o-mini-transcribe , and gpt-4o-transcribe-diarize integrations also support file streaming. whisper-1 doesn’t.”
Speech to text (OpenAI API guide), OpenAI, OpenAI, 2026, Streaming transcriptions section.
Open the original- What it measures
- The guide separates file streaming, which returns partial text while a finished recording is processed, from realtime transcription for live audio.
- What it does not show
- This describes OpenAI's hosted API. The open-source Whisper package processes a whole file in 30-second windows and does not expose a streaming output in the same way.