Model · OpenAI · Speech-To-Text
GPT Transcribe
OpenAI's current hosted transcription model and the named replacement for GPT-4o Transcribe. Priced per minute of audio rather than per token, for batch and file-based transcription.
- Modality
- Speech-To-Text
- License
- Proprietary (Proprietary)
- Released
- July 28, 2026
- Last verified
- September 8, 2026
- Runs locally
- No
Strengths
- Per-minute pricing at $0.0045/min — simpler to budget than token-based transcription
- OpenAI's named successor to the retiring GPT-4o Transcribe line
- Available on both the transcriptions endpoint and realtime transcription sessions
Weaknesses
- OpenAI does not publish a context window or max output for this model
- Closed weights — no self-hosting, unlike the Whisper checkpoints
- Transcription only; no audio question-answering or understanding
Try it
| Where | Type | Notes |
|---|---|---|
| OpenAI API | hosted-api | API key required |
Used in solutions
Version history
- GPT Live Transcribe Jul 2026
- GPT Transcribe Jul 2026 Current
Official sources
- Model docs docs
- API deprecations docs
Change log
- — Initial entry. Released 2026-07-28. Named on OpenAI's deprecations page as the replacement for gpt-4o-transcribe (shutdown 2027-02-26). Context window and max output are not published by OpenAI, so both are left unset.
Esc