GPT-Realtime

Voice & speech playground

Hydrating page from local storage...

Have a low-latency voice conversation, interrupt spoken responses, or send text in the same live session.

Microphone access requires HTTPS or localhost and your permission. Audio is sent to the selected provider only when you submit a request or start a live session. Use headphones for live conversations.

Find models in Microsoft Foundry. Foundry speech API guide

Connection

Use an OpenAI endpoint or a Foundry resource with the selected speech deployment.

Endpoint

Model / deployment name

Authentication Mode

API Key

Advanced

Speech controls

Voice

Choose a built-in voice, or select Custom to enter another documented voice ID. Grok also accepts an existing authorized custom voice ID.

Turn detection

Input transcription deployment (optional)

Enter an available transcription deployment to show what you say as text. Leaving this empty still enables voice conversation.

System instructions

Ready. Configure your connection to begin.

Text message (optional)

Provider usage is billable. No estimated price is assumed; returned usage is available in Payloads.

Transcripts and captured speech will appear here. Configure your endpoint, then record or start a live session.