MODELS / XAI

Grok STT

Transcribe audio to text in 25 languages with batch and streaming modes.

TRANSCRIPTIONWEBSOCKET-TRANSCRIPTION
—
CONTEXT WINDOW
—
MAX OUTPUT TOKENS
Free
INPUT PRICE
—
OUTPUT PRICE
QUICKSTART

Call it in one request.

OpenAI-compatible — change the base URL, and the setup is complete.

SHELL
curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/xai/grok-stt",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
INPUT: audioOUTPUT: textRELEASED: 2026-03-16
RELATED MODELS

Also worth a look.

XAI

Grok 4.1 Fast Non-Reasoning

1M context · $0.2 / 1M tokens input · $0.5 / 1M tokens output

XAI

Grok 4.1 Fast Reasoning

1M context · $0.2 / 1M tokens input · $0.5 / 1M tokens output

XAI

Grok 4.20 Beta Non-Reasoning

— context · $1.25 / 1M tokens input · $2.50 / 1M tokens output