Skip to content
AI News HubLIVE
More
Summary only

OpenAI's new voice model brings GPT-5-level reasoning to real-time conversations

OpenAI has released three new real-time voice models: GPT-Realtime-2, which delivers GPT-5-level reasoning; GPT-Realtime-Translate for live translation across 70+ languages; and GPT-Realtime-Whisper for streaming transcription. The models are available through OpenAI's Realtime API.

SourceThe DecoderAuthor: Matthias Bastian
OpenAI's new voice model brings GPT-5-level reasoning to real-time conversations
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersBeginner

Key points

  • OpenAI introduces three real-time voice models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper
  • GPT-Realtime-2 offers GPT-5-level reasoning with a 128K context window and adjustable reasoning intensity across five levels
  • GPT-Realtime-Translate supports live translation for over 70 input languages and 13 output languages
  • All models are now available via the Realtime API, with pricing on tokens or per minute

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models

OpenAI's new voice model brings GPT-5-level reasoning to real-time conversations | AI News Hub