OpenAI adds GPT-Live-Transcribe and GPT-Transcribe for lower-latency audio transcription

OpenAIDevs · x · 2026-07-29

OpenAI introduced two new transcription models in its API:

The company says both models better use context and improve accuracy on real-world audio across accents and languages. On its new Context Aware ASR benchmark, GPT-Live-Transcribe’s semantic accuracy rose from 38.5% without free-form context to 44.6% with it.

Other reported results:

OpenAI also says builders can improve live transcription by supplying free-form recording context, keywords, expected input languages, and earlier transcribed turns.

Related event: OpenAI Launches New Transcription Models with Improved Accuracy and Lower Prices(15 posts)→

Original post →

More from Models

Models channel →