Source: OpenAI Speech-to-Text Guide
OpenAI API guide to transcription: current and deprecated STT models, 25 MB file limit, prompting with keywords, diarization, streaming and realtime transcription.
Contents
- What: official API documentation (Speech to text guide)
- Author/publisher: OpenAI
- Date: living document; read 2026-11-14
- Original: Speech to text
Summary
Covers file transcription via /v1/audio/transcriptions, live transcription through Realtime sessions, and the migration away from Whisper-era models.
Key claims
- Models (as of 2026-11):
gpt-transcribefor recorded audio,gpt-live-transcribefor live audio via Realtime transcription,gpt-realtime-translatefor speech translation. whisper-1,gpt-4o-transcribe,gpt-4o-mini-transcribeandgpt-4o-transcribe-diarizeare deprecated with shutdown on 2027-02-26.- Files up to 25 MB; formats flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Split longer audio without cutting mid-sentence.
- Context:
prompt(free text),keywords(literal-term hints, which can occasionally cause unspoken terms to appear) andlanguages.whisper-1prompts are limited to 224 tokens; a text model can post-process transcripts for terminology. - Word/segment timestamps (
timestamp_granularities[]) only on the deprecatedwhisper-1. - Diarization:
diarized_jsonwith speaker, start, end; up to 4 known-speaker reference clips of 2-10 s; not available in Realtime sessions. - Streaming file transcription emits
transcript.text.delta/.doneevents.