Modelpeers

GPT Transcribe and GPT Live Transcribe

2 models from OpenAI

New release

GPT Transcribe and GPT Live Transcribe released

OpenAI released GPT Transcribe for file transcription and final transcripts of committed Realtime turns, and GPT Live Transcribe for low-latency streaming transcription. Both support transcription context, keyword hints and multiple expected input languages.

Who is affected:
Apps that transcribe audio with the OpenAI API, including users of the older transcription models scheduled to shut down.
What to do:
Evaluate these models as replacements for whisper-1 and the GPT-4o transcribe models.

Source

"for low-latency streaming transcription. Both models support free-form transcription context, keyword hints, and multiple expected input languages."

OpenAI API changelog

Published

Open the sourcedevelopers.openai.com

Modelpeers tracks changes to AI agents and models, each from its source. Follow GPT Transcribe to get a weekly email when it changes.