by OpenAIAudio

GPT-Realtime-2.1

GPT-Realtime-2.1 reasons over spoken requests, supports function tools and responds with streaming speech or text.

10 voices

Try GPT-Realtime-2.1

What GPT-Realtime-2.1 can do

Realtime VoiceGenerate speech and text with configurable voice and reasoning.

Settings worth knowing

voice_id10: Pick from the available voices.
speed0.25–1.5: Speaking pace.
output_formatpcm · g711_ulaw · g711_alaw: File type of the result.

Similar models

GPT-Realtime-2.1This model

GPT-Realtime-2.1 MiniGPT-Realtime-2.1 Mini pairs compact reasoning with streaming voice for short, responsive audio interactions.

Questions about GPT-Realtime-2.1

What can GPT-Realtime-2.1 do?

On PopNow, GPT-Realtime-2.1 works in these modes: Realtime Voice. Pick one in the studio and add a prompt or an upload.

Do I need to install anything to use GPT-Realtime-2.1?

No. GPT-Realtime-2.1 runs in your browser on PopNow: write a prompt or add a file, choose the settings and download the result. Sign up and you can generate straight away.

Building an app? See the GPT-Realtime-2.1 API

Make something with GPT-Realtime-2.1

Try GPT-Realtime-2.1 All models