# Word-Level Timestamps for Karaoke & TikTok Captions

**Use case:** 

Need word-by-word captions that pop in sync? This returns per-word start and end times for animated TikTok and Reels karaoke subtitles.

## Input

```json
{
  "mediaUrl": "https://cdn.example.com/reels/clip-music.mp4",
  "language": "en",
  "wordTimestamps": true,
  "outputFormats": [
    "srt",
    "vtt"
  ],
  "model": "whisper-1"
}
```

## Output

```json
{
  "language": {
    "label": "Language"
  },
  "wordCount": {
    "label": "Word count"
  },
  "segmentCount": {
    "label": "Segment count"
  },
  "durationSeconds": {
    "label": "Duration seconds"
  },
  "srtUrl": {
    "label": "Srt url"
  },
  "vttUrl": {
    "label": "Vtt url"
  },
  "text": {
    "label": "Text"
  }
}
```

## About this Actor

This example demonstrates how to use [Video & Audio Transcriber — Word-Level + SRT/VTT](https://apify.com/dami_studio/video-audio-transcriber) with a specific input configuration. Visit the [Actor detail page](https://apify.com/dami_studio/video-audio-transcriber) to learn more, explore other use cases, and run it yourself.