> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vidjutsu.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# transcribeMedia

> Speech-to-text with word-level timing.

## Usage

```typescript theme={null}
const { data, error } = await vj.transcribeMedia({
  mediaUrl: "https://cdn.example.com/video.mp4",
});
```

## Parameters

| Field      | Type     | Required | Description                                                   |
| ---------- | -------- | -------- | ------------------------------------------------------------- |
| `mediaUrl` | `string` | Yes      | URL of the video or audio to transcribe                       |
| `language` | `string` | No       | Language code (e.g. `"en"`, `"es"`). Auto-detected if omitted |

## Response

```json theme={null}
{
  "transcript": "the one thing nobody tells you about creatine",
  "words": [
    { "word": "the", "start": 0.1, "end": 0.2 },
    { "word": "one", "start": 0.22, "end": 0.35 },
    { "word": "thing", "start": 0.37, "end": 0.52 }
  ],
  "language": "en",
  "duration": 10.2
}
```

## Rate limit

Counts toward the daily `transcribe` limit (30/day). Resets at 00:00 UTC; exceeding it returns HTTP 429.