# Grok Speech to Text

> Run Grok Speech to Text by xai online or via API. $0.10/hr of audio for files, $0.20/hr for realtime, no setup.

**URL:** https://inference.sh/apps/xai/grok-stt
**Last updated:** 2026-11-11

---

Transcribe speech with xAI's Grok Speech to Text. Send a recording and get the transcript with word timings and speakers, or stream a microphone over a socket and read the transcript as it is spoken.

- app: `xai/grok-stt`
- maker: [xai](https://inference.sh/apps/xai.md)
- category: [audio](https://inference.sh/apps/category/audio.md)
- input → output: speech → text
- tasks: [speech to text](https://inference.sh/apps/tag/speech-to-text.md), [realtime](https://inference.sh/apps/tag/realtime.md)
- price: $0.10/hr of audio for files, $0.20/hr for realtime
- runs via: api, javascript and python sdk, belt cli, mcp

## grok-stt API Guide

### About
transcribe speech with xai's grok speech to text. send a recording and get the transcript with word timings and speakers, or stream a microphone over a socket and read the transcript as it is spoken.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @3d801pnz pinned
result = client.run({
        "app": "xai/grok-stt@3d801pnz",
        "input": {
            "audio": "https://example.com/file.png"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @3d801pnz pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "xai/grok-stt@3d801pnz",
        "input": {
            "audio": "https://example.com/file.png"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "xai/grok-stt@3d801pnz",
        "input": {
            "audio": "https://example.com/file.png"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "xai/grok-stt@3d801pnz",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **audio** (string) *required*: The recording: wav, mp3, ogg, opus, flac, aac, m4a, mp4 or mkv, up to 500 MB
- **language** (string): What is spoken. Speech is transcribed in any supported language without it; naming it writes numbers, currencies and units the way they are written ("$167,983.15").
- **diarize** (boolean): Tell speakers apart: each word carries a speaker number
- **keyterms** (array): Names and terms the transcript should prefer, up to 100 of at most 50 characters each
- **filler_words** (boolean): Keep fillers such as "um" and "uh"

#### Output
- **duration** (number): Length of the audio, in seconds
- **language** (string): The language xAI detected, such as en or es-mx
- **text** (string): The transcript
- **words** (array): Every word with its timing

## other audio apps

- [Pika H3 Flex Audio Stems](https://inference.sh/apps/pika/pika-h3-flex-audio-stems.md): $0.001/stem-sec (3 stems: dialogue, music, effect)
- [Fish Audio Drama 3](https://inference.sh/apps/fish-audio/drama-3.md): $50.00/1M UTF-8 bytes
- [Eleven Flash v2.5](https://inference.sh/apps/elevenlabs/eleven-flash-v2-5.md): $0.04/1K characters
- [Eleven Multilingual v2](https://inference.sh/apps/elevenlabs/eleven-multilingual-v2.md): $0.08/1K characters
- [Eleven v3](https://inference.sh/apps/elevenlabs/eleven-v3.md): $0.08/1K characters

## faq

### how much does Grok Speech to Text cost?

$0.10/hr of audio for files, $0.20/hr for realtime. you pay per run from your inference shell credits. no subscription is required.

### how do I run Grok Speech to Text via api?

call xai/grok-stt with the javascript or python sdk, the rest api, or `belt app run xai/grok-stt` from a terminal. the api reference on this page lists every input.

### who makes Grok Speech to Text?

Grok Speech to Text is made by xai and runs on inference shell. every xai app is listed at https://inference.sh/apps/xai.

### can my agent use Grok Speech to Text?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Grok Speech to Text?

other audio apps on inference shell include Pika H3 Flex Audio Stems, Fish Audio Drama 3, Eleven Flash v2.5, Eleven Multilingual v2. they run through the same api, so switching is a one-line change.
