Model releaseHigh global significanceConfirmed confidence
OpenAI releases GPT-4o Transcribe
OpenAI releases a new generation of GPT-4o-based speech-to-text models.
What happened
Event details
The model improves recognition reliability across accents, noisy environments and different speaking speeds and is available to developers through the Audio API.
Assessment
Why it matters
It applies the GPT-4o architecture to specialized ASR and substantially advances multilingual transcription accuracy in a commercial API.
76/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.
Availability
Access notes
Available through the OpenAI Audio API; local weights are not released.