GPT-Realtime-Translate

OpenAI

OpenAI's streaming speech-to-speech translation model, taking spoken input in one language and producing spoken output in another without an intermediate text round trip, for live interpretation and multilingual conversation.

Strengths

Streaming speech-to-speech translation with no intermediate text round trip
Built for live interpretation and multilingual conversation
Part of OpenAI's realtime audio family

Caveats

Proprietary - OpenAI API only
Purpose-built for translation rather than general conversation
OpenAI's model reference states no supported-language list, context window or price

Vendor: OpenAI
License: Proprietary
Modalities: audio
text

Capabilities

Vision

Audio

Video

Tool Use

Resources

API Documentation

Pricing

Usage-based realtime audio pricing via the OpenAI API; rates are not published on the model reference page.