GPT Transcribe

High-accuracy speech-to-text model for file and Realtime input transcription

GPT Transcribe is OpenAI's high-accuracy speech-to-text model for completed audio files, streamed file transcripts, and committed turns in Realtime sessions; it supports context prompts, keyword hints, and multiple language hints.

Pricing

Official site · Jul 29, 2026, 7:30 AM

Per minute

$0.0045

Official OpenAI pricing for transcription audio duration: $0.0045 per minute.

OpenAI's official GPT Transcribe model documentation identifies model ID `gpt-transcribe` as a speech-to-text model and lists transcription audio duration pricing at $0.0045 per minute; the official API pricing page corroborates `gpt-transcribe` at $0.0045 / minute.

View source

Model Intelligence

Benchmarkable

Yes

Model level

release

Recent stories

1 linked story

releasePRIMARY2026-07-28

OpenAI releases GPT-Transcribe API at 3.31% AA-WER and $4.50 per 1,000 minutes

OpenAI released GPT-Live-Transcribe and GPT-Transcribe in the API for streaming and offline speech recognition. The launch adds context prompts, keywords, language hints, and WER gains, with Artificial Analysis reporting GPT-Transcribe at 3.31% AA-WER and $4.50 per 1,000 audio minutes.