Grok Voice Transcribe

The spoken language, as a code such as en or es. Leave as Auto to have the model detect it.

Label each word with a speaker index when multiple people talk.

Convert spoken numbers and currency into written form (e.g. "one hundred dollars" → "$100"). Requires a language.

Names, products and terms the audio contains, so the model spells them right.

Add per-word start/end times and confidence inside each transcript segment. Increases the size of the result considerably.

Also return the transcript as a subtitle file, SRT or WebVTT, timed to the audio.