OpenAI Launches GPT-Live-Transcribe and GPT-Transcribe Models for Accurate Audio Transcription

_rchaves_ · x · 2026-07-29

OpenAI introduces two new transcription models in the API:

• GPT-Live-Transcribe: built for low-latency live transcription.
• GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads.

Both models deliver more accurate transcription on real-world audio across accents and languages, including short phrases, numbers, and proper nouns.

Related event: OpenAI Launches GPT-Transcribe and GPT-Live-Transcribe Speech Transcription Models(16 posts)→

Original post →