Voice and music · by OpenAI
OpenAI transcription
Transcribe audio with spelling hints, or translate live speech.
speech → text, data · speech → text, events · speech → text, speech
- Way in
- Official APISign up yourself, api key
- To start
- $none
- Runs
- In the cloudAlso through Azure
- Checked
- Nov 3, 2026Prices as of that day
What it can do 4
Transcribe an audio file with prompt/keyword hints and language detection25 MB per file; mp3/mp4/mpeg/mpga/m4a/wav/webmspeech → text, data$0.0045/min (gpt-transcribe)
Transcribe live audio in realtimeRealtime API (WebSocket/WebRTC)speech → text, events$0.017/min (gpt-live-transcribe or gpt-realtime-whisper)
Translate live speech into another languagespeech → text, speech$0.034/min (gpt-realtime-translate)
Diarized transcription with speaker labels (legacy)deprecated, shuts down 2027-02-26speech → data~$0.006/min (gpt-4o-transcribe-diarize)
Does the same job
Prices and limits as of Nov 3, 2026, from OpenAI’s own pages. They change; check before you rely on them.Not affiliated with OpenAI. Not advice.Rankings: Artificial Analysis.Something wrong?