Model releaseCritical global significanceConfirmed confidence
OpenAI launches GPT-4o Realtime Preview
OpenAI opens the Realtime API public beta for low-latency, native speech-to-speech interaction.
What happened
Event details
The model directly processes and generates audio within a single real-time session, replacing a chained ASR, text-model and TTS pipeline while automatically handling interruptions and supporting function calls.
Assessment
Why it matters
It gave API developers their first native low-latency speech-to-speech path and established OpenAI's real-time voice-model product line.
85/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.
Availability
Access notes
Opened as the Realtime API public beta on October 1, 2024; later succeeded by production models including gpt-realtime.