GPT-Live-Transcribe

Voice & speech playground

Hydrating page from local storage...

Read live microphone captions. Audio turns are committed on a client-side interval or with Finish turn; this model does not use server VAD.

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

Expected source languages (optional)

OpenAI documents code examples without a complete language list. Choose a suggestion, or select Custom to enter one or more comma-separated source-language codes. These hints guide recognition of the original speech. Automatic language detection sends no language hint.

Vocabulary hints (one per line)

Transcription context (optional)

These models do not expose speaker labels or word timestamps. Use MAI-Transcribe or Grok Speech to Text for those features.

Transcription delay

Commit audio every (seconds)

Client-side commits finalize captions without unsupported server VAD. Finish turn also commits manually.

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.