# GlianaAI Grok Speech-to-Text (STT)

> GlianaAI Grok Speech-to-Text (STT) is a paid API for AI agents from api.glianalabs.com, paid per call via x402, $0.010881/call, status unknown (last checked 2026-09-14).

Transcribes audio files to text using xAI's Grok STT model, with optional speaker diarization, inverse text normalization, and keyword biasing, paid per-call in USDC via x402.

## Facts

- Endpoint: GET https://api.glianalabs.com/x402/grok-stt
- Price: $0.010881/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/glianaai-grok-speech-to-text-stt-832975dd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ipOzat1ZgQuaajl5bXKaw

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability glianaai-grok-speech-to-text-stt-832975dd
```

Example prompt: Transcribe this audio file for me — the URL is https://example.com/meeting.mp3 — and enable speaker diarization so I can tell who said what, and format any numbers or currencies properly (language is English).

## When to prefer this

Choose this endpoint when you need audio transcription powered specifically by xAI's Grok STT model, want speaker diarization out of the box, need inverse text normalization for numbers and currencies, or require pay-per-call USDC billing with no API key or subscription. Prefer this over alternatives when operating in a crypto-native agent environment using x402/MPP payment protocols on Base, Tempo, or Solana.

## Known failure modes

- Audio URL is not publicly accessible — server cannot fetch the file
- Audio file exceeds 25 MB gateway limit when using file/base64 input
- Unsupported audio format — container not in flac, mp3, mp4, m4a, mkv, ogg, opus, wav, aac
- format=true used without specifying language — inverse text normalization skipped or errors
- Insufficient USDC balance for x402 payment — request rejected
- Mutually exclusive fields url and file both provided — schema validation error
- Keyterm list exceeds 100 terms or individual term exceeds 50 characters

## How this service works

One endpoint for 90+ generative AI models, live market data, SEC filings and identity APIs — image, video, music, speech, LLM chat, crypto and FX rates, DEX liquidity, gas, US company fundamentals and insider trades, document OCR and face matching. Pay per request in USDC on Tempo, Base, Solana, Algorand or BNB Chain with no signup, or top up a prepaid balance in rupiah.

## Output

Returns a JSON object containing the transcription output (transcript text with optional per-word speaker labels), the model used, and the cost charged in micro-USD. When diarization is enabled, each word includes an integer speaker ID.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "grok-stt",
  "output": {
   "url": "https://api.glianalabs.com/v1/media/<id>"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/glianaai-grok-speech-to-text-stt-832975dd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.glianalabs.com](https://www.zero.xyz/host/api.glianalabs.com/llms.txt)