xAI

Grok Voice STT 1.0

Generally availableProprietary15K context

Summary

Grok Voice STT 1.0 is a proprietary language model from xAI, released on 4 Aug 2026. It accepts audio and generates text, with a 15K-token context window and up to 15K output tokens per response.

Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.

Last verified 19 Oct 2026. Every figure on this page links to its source.

Specifications

DeveloperxAI
Release date4 Aug 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window15K (15,000 tokens) [models.dev]
Max output15K tokens [models.dev]
InputAudio [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Grok Voice STT 1.0 API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of Grok Voice STT 1.0?

Grok Voice STT 1.0 has a context window of 15,000 tokens (15K) and can generate up to 15,000 tokens in a single response, according to models.dev.

Is Grok Voice STT 1.0 open source?

No. Grok Voice STT 1.0 is a proprietary model; xAI has not released its weights.

When was Grok Voice STT 1.0 released?

xAI released Grok Voice STT 1.0 on 4 Aug 2026, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Gemini 3.5 Live Translate PreviewGoogle DeepMind9 Jun 202616K$3.50$21Closed
gpt-realtime-whisperOpenAI7 May 202616K––Closed
GPT Live Transcribe (OpenAI)OpenAI28 Jul 2026–––Closed
Voyage Rerank 3Voyageai30 Sept 202632K––Closed
Voyage Rerank 3 LiteVoyageai30 Sept 202632K––Closed
Gemini 3.5 Transcribe LiveGoogle DeepMind26 Aug 2026–––Closed

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources