# GPT-Transcribe

OpenAI, released 2026-07-28

**Verdict: recommended.** OpenAI's latest batch speech-to-text model scores 3.31% AA-WER at $0.0045/min — 25% cheaper and measurably more accurate than its gpt-4o-transcribe predecessor. It supports context prompting, keyword hints, and language detection across 22+ languages, making it the best default for asynchronous file transcription on the OpenAI platform. Caveat: no diarization or word-level timestamps; use gpt-4o-transcribe-diarize for speaker labels or gpt-live-transcribe for real-time needs. Best for developers building meeting transcription, media processing, and voice interfaces on the OpenAI API. Last verified 2026-07-29.

## Pricing

- Input: $0.0045 / minute
- Output: N/A
- Context: Per-minute audio billing

## Strengths

- High-accuracy batch transcription with 3.31% AA-WER across diverse audio conditions
- Context-aware transcription via free-form prompts, keywords, and language hints for domain-specific audio
- 22+ language support with detected-language output on completion
- 25% cheaper than predecessor gpt-4o-transcribe at $0.0045/min
- Multilingual code-switching, noisy audio, or long-form earnings-call audio where specialized models outperform
- Multi-speaker meetings requiring speaker diarization — use gpt-4o-transcribe-diarize instead
- Real-time streaming transcription needing sub-second latency — use gpt-live-transcribe

## Benchmarks

- AA-WER v2: 3.31% (https://artificialanalysis.ai/speech-to-text/non-streaming)
- AA-AgentTalk WER: 2.22% (https://x.com/ArtificialAnlys/status/2082285338509418727)
- VoxPopuli-Cleaned-AA WER: 2.72% (https://x.com/ArtificialAnlys/status/2082285338509418727)
- Earnings22-Cleaned-AA WER: 6.10% (https://x.com/ArtificialAnlys/status/2082285338509418727)
- Common Voice 22-language TER: 19.27% (https://x.com/OpenAIDevs/status/2082201169443905798)
- Context Aware ASR (semantic accuracy): 45.2% (https://x.com/OpenAIDevs/status/2082201169443905798)

## Sources

- [OpenAI API — Realtime Transcription Guide](https://developers.openai.com/api/docs/guides/realtime-transcription)
- [OpenAI Developers on X: GPT-Transcribe + GPT-Live-Transcribe announcement](https://x.com/OpenAIDevs/status/2082201169443905798)
- [Artificial Analysis — Speech-to-Text Leaderboard](https://artificialanalysis.ai/speech-to-text/non-streaming)
- [Artificial Analysis on X: GPT Transcribe benchmarks](https://x.com/ArtificialAnlys/status/2082285338509418727)
- [GIGAZINE — GPT Transcribe / GPT Live Transcribe Release Coverage](https://gigazine.net/news/20260729-gpt-live-transcribe/)
- [OpenAI API pricing page (transcription models)](https://developers.openai.com/api/docs/pricing)
- [OpenAI API — GPT Transcribe Model Page](https://developers.openai.com/api/docs/models/gpt-transcribe)

Canonical: https://neomanex.com/models/gpt-transcribe