Speech to Text
Audio transcription and speech recognition models.
Endpoints: /v1/audio/transcriptions
Live catalogue
Availability is a generated snapshot from 2026-10-15. Prices are intentionally not copied into static pages because Admin-reviewed rates can change independently of a docs release. Read the public catalogue for current billing units, availability, and customer prices.
Available (5)
| Model | ID | Context | Protocols | Capabilities |
|---|---|---|---|---|
| GPT Transcribe | gpt-transcribe | — | openai_audio | speech_to_text |
| GPT-4o Transcribe | gpt-4o-transcribe | — | openai_audio | speech_to_text |
| GPT-4o Transcribe (Diarize) | gpt-4o-transcribe-diarize | — | openai_audio | speech_to_text, speaker_diarization |
| GPT-4o Mini Transcribe | gpt-4o-mini-transcribe | — | openai_audio | speech_to_text |
| Whisper (Speech to Text) | whisper | — | openai_audio | speech_to_text |