GPT-4o Transcribe
GPT-4o Transcribe is a deprecated speech-recognition model based on GPT-4o. It produces text from audio and can use text context.
Deprecated API; check access details
A transcription model with a bounded output
Its published context is 16,000 tokens and maximum output is 2,000 tokens. The documentation positions it as an improvement over the original Whisper models for recognition accuracy. That claim does not establish accuracy on a specific recording.GPT-4o Transcribe official model documentation
Review an existing integration
Practical guidance. Review accents, specialist terms and noisy speech from the actual application. A migration should preserve meaningful punctuation and numbers as well as words. Keep a way to inspect the original recording when the transcript affects an important decision.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Access | API |
| Model identifiers | gpt-4o-transcribe |
| Context window | 16,000 tokens Published context for this deprecated release GPT-4o Transcribe official model documentation |
| Maximum output | 2,000 tokens Published maximum output, bounded by the remaining context GPT-4o Transcribe official model documentation |
| Provider status | Deprecated in the current OpenAI model catalog; confirm remaining account access.GPT-4o Transcribe official model documentation |
Related models
- GPT-Transcribe
OpenAI · GPT transcription
GPT-Transcribe turns recorded speech into text.
Launch date not confirmedAPI - GPT-Live-Transcribe
OpenAI · GPT transcription
GPT-Live-Transcribe produces incremental text from live audio.
Launch date not confirmedAPI - GPT-Realtime-Whisper
OpenAI · GPT transcription
GPT-Realtime-Whisper is a streaming transcription model for live speech.
Launch date not confirmedAPI