Remy Reference/models/Grok STT

Grok STT

Grok STT, a transcription model from X.ai.

transcriptionModelOverride: { model: "grok-stt" }

XX.ai·Released 2026

Pricing

List price: $0.10 / hour
Per second: $0.000028
Per minute: $0.0017
Per second: $0
Per minute: $0

Specifications

Released: 2026
Model string: grok-stt-1.0
Capabilities: Low cost

Parameters

Model options, passed in transcriptionModelOverride.config.

Parameter	Type	Default	Range / options
`language` Used with text formatting. Leave as Auto unless you want inverse-text-normalization in a specific language.	Select	—	enesfrdejako+4
`includeSpeakers` Label each word with a speaker index when multiple people talk.	Select	no	yesno
`format` Convert spoken numbers and currency into written form (e.g. "one hundred dollars" → "$100"). Requires a language.	Boolean	false

Use this model

await mindstudio.transcribeAudio({
  audioUrl: "...",
  transcriptionModelOverride: {
    model: "grok-stt",
    config: {
      includeSpeakers: "no",
    },
  },
});