GPT-Transcribe
GPT-Transcribe turns recorded speech into text. It supports complete files, streamed file transcripts and committed audio turns in Realtime sessions.
Context can help with terms and language changes
The model accepts free-form context, keyword hints and multiple language hints. Its listed charge is $0.0045 per audio minute. It is available through file transcription and Realtime transcription endpoints and returns text only.GPT-Transcribe official model documentation
Supply vocabulary without dictating the answer
Practical guidance. For an interview about a specialist topic, provide relevant names and technical terms. Review passages where the speaker changes language or corrects a number. Keep the audio available to a reviewer instead of treating a polished transcript as proof of accuracy.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | gpt-transcribe |
| Input and output | audio, text in; text outGPT-Transcribe official model documentation |
| API routes | Realtime transcription (v1/realtime/transcription_sessions); Transcription (v1/audio/transcriptions)GPT-Transcribe official model documentation |
Related models
- 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