GPT-Talk
ChatGPTGPT ModelsCodexAPIPromptMemoryMCPRelease Notes

Voice

Realtime Voice and voice mode

GPT-Realtime-2.1 is OpenAI's current low-latency voice API family — it supports interruption, tone detection, and laugh responses, and powers ChatGPT Voice Mode. This channel covers the difference between the Realtime API and ChatGPT Voice Mode, WebRTC vs WebSocket selection, and mid-conversation function calling in practice.

GPT-Realtime-2.1WebRTC vs WebSocketVoice ModeThe six voicesEphemeral TokenFunction Calling

1 article(s) total

Voice
2 min

Realtime Voice guide: gpt-realtime and Voice Mode

How to ship low-latency voice AI with OpenAI's gpt-realtime / gpt-realtime-mini: WebRTC vs WebSocket, mid-conversation function calling, and Voice Mode best practices.

Read article