Grok Live Transcribe

Voice & speech playground

Hydrating page from local storage...

Stream microphone captions with interim results, speaker labels, vocabulary hints, text formatting, VAD, and Smart Turn endpointing.

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.

Connection

Use the native SpaceXAI endpoint.

Endpoint

Model / deployment name

Authentication Mode

API Key

Advanced

Speech controls

Source language hint (optional)

Choose a documented language or locale, or select Custom to enter another provider-supported code. This hint identifies the spoken source language. Automatic language detection sends no language hint.

Vocabulary hints (one per line)

Identify speakers (diarization) Format numbers and currencies (requires language) Keep filler words

VAD threshold (optional)

0 disables the voice gate. Provider defaults: 0.5 for files, 0.08 for streaming.

Interim captions

Silence endpointing (ms)

Smart Turn threshold (optional)

Smart Turn timeout (ms, optional)

Microphone streaming uses mono PCM16 at 24 kHz through a same-origin, header-authenticated relay. Use file transcription for multichannel recordings. Finish turn sends the documented finalize event.

Ready. Configure your connection to begin.

Estimated cost Unavailable(Reported Cost: Unavailable)

xAI streaming transcription: $0.20/hour. Estimate uses provider audio duration or captured microphone duration.

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