# Batch audio transcription and subtitles

**Use case:** 

Transcribe multiple real media files and create subtitle artifacts for an accessibility or content workflow.

## Input

```json
{
  "mediaUrls": [
    {
      "url": "https://raw.githubusercontent.com/ggerganov/whisper.cpp/master/samples/jfk.wav"
    },
    {
      "url": "https://raw.githubusercontent.com/Jakobovski/free-spoken-digit-dataset/master/recordings/9_yweweler_49.wav"
    }
  ],
  "language": "auto",
  "outputFormats": [
    "srt",
    "vtt"
  ],
  "maxFileSizeMb": 250,
  "maxDurationMinutes": 10
}
```

## Output

```json
{
  "sourceUrl": {
    "label": "Source URL",
    "format": "string"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "transcript": {
    "label": "Transcript",
    "format": "string"
  },
  "language": {
    "label": "Language",
    "format": "string"
  },
  "durationSeconds": {
    "label": "Duration (seconds)",
    "format": "number"
  },
  "segments": {
    "label": "Segments",
    "format": "array"
  },
  "srtKey": {
    "label": "SRT key",
    "format": "string"
  },
  "vttKey": {
    "label": "VTT key",
    "format": "string"
  },
  "processingSeconds": {
    "label": "Processing time",
    "format": "number"
  },
  "error": {
    "label": "Error",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [Audio Speech-to-Text Transcriber](https://apify.com/automation-lab/audio-speech-to-text-transcriber) with a specific input configuration. Visit the [Actor detail page](https://apify.com/automation-lab/audio-speech-to-text-transcriber) to learn more, explore other use cases, and run it yourself.