GPT-Realtime-Translate

Voice & speech playground

Hydrating page from local storage...

Translate continuous microphone audio into spoken output and captions. This is an interpreter, not a conversational assistant.

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

Source transcription model / deployment (optional)

Use a supported transcription model or deployment to also show the original speech as text. Leave empty for translated captions only.

Input noise reduction

Near-field suits a headset or close-talking microphone; far-field suits a laptop or conference-room microphone.

Translate into

OpenAI's translation guide gives Spanish and French examples without a complete target-language list. Choose a suggestion, or select Custom to enter another supported code. Source language is detected automatically.

Ready. Configure your connection to begin.

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.