models/xAI/Grok STT
xAI

Grok STT

audio-stt
Compare

xAI's Grok speech-to-text model. Transcribes audio files into text across 25 languages with word-level timestamps, multichannel transcription, speaker diarization, and key-term biasing.

MODALITIES
audio
RELEASED
2026-06-03

Grok STT (xai/grok-stt) is a audio-stt model from xAI, released 2026-06-03. Pricing via AIgateway: $0.0017 per minute. Call it via https://api.aigateway.sh/v1/audio/transcriptions — set model="xai/grok-stt". Best for: Meeting transcripts, Captions, Voice agents.

model · xai/grok-stt

Use this model

model: xai/grok-stt
curl https://api.aigateway.sh/v1/audio/transcriptions \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -F model="xai/grok-stt" \
  -F file="@audio.mp3"

Capabilities

Strengths

  • Speech-to-text transcription

Use cases

Meeting transcriptsCaptionsVoice agents

Pricing

Per minute$0.0017
You pay pass-through · 5% applied at credit top-up, not per-call.
See API example →CompareAPI referenceSee usage ranking →

Collections

More audio models →More from xAI →Frontier models →Free-tier models →
API schema

Call Grok STT from any OpenAI SDK

POST https://api.aigateway.sh/v1/audio/transcriptions·Content-Type: multipart/form-data·Auth: Bearer sk-aig-...

Request body

json
# multipart/form-data — use curl -F or SDK file upload
model="xai/grok-stt"
file=@audio.mp3
response_format=json    # or "verbose_json", "text", "srt", "vtt"
language=en             # optional

Response

json
{
  "text": "Hello from AIgateway.",
  "language": "en",
  "duration": 1.82
}

Quickstart

from openai import OpenAI
client = OpenAI(base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...")

with open("audio.mp3", "rb") as f:
    r = client.audio.transcriptions.create(model="xai/grok-stt", file=f)
print(r.text)

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is Grok STT?
xAI's Grok speech-to-text model. Transcribes audio files into text across 25 languages with word-level timestamps, multichannel transcription, speaker diarization, and key-term biasing. It is a audio-stt model from xAI, accessible via AIgateway's OpenAI-compatible API at slug xai/grok-stt.
How much does Grok STT cost via AIgateway?
$0.0017 per minute of audio. Pass-through plus a 5% platform fee applied at top-up.
How do I call Grok STT from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "xai/grok-stt". The request and response shapes match OpenAI exactly.
Does Grok STT support streaming, tool calling, vision, and JSON mode?
Streaming — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
What are the best use cases for Grok STT?
Meeting transcripts, Captions, Voice agents. Key strengths: Speech-to-text transcription.
Can I bring my own xAI API key (BYOK)?
Yes. Attach a xAI key in your AIgateway dashboard and this model flips to pass-through — you pay xAI directly and AIgateway waives the 5% platform fee on those calls.