# Transcribe Interview Audio to Text with Speaker Labels

**Use case:** 

Convert interview or podcast audio to text with speaker labels and an AI summary. Provide any public audio URL and get a clean, diarized transcript back.

## Input

```json
{
  "audioUrls": [
    "https://archive.org/download/FrankDaleGWMediaDay-InterviewwithKimberlyBeck/kimbeckinterview.mp3"
  ],
  "model": "nova-3",
  "language": "en",
  "detectLanguage": false,
  "diarize": true,
  "smartFormat": true,
  "paragraphs": true,
  "summarize": true,
  "includeSrt": false,
  "includeUtterances": false,
  "includeWords": false
}
```

## Output

```json
{
  "url": {
    "label": "File",
    "format": "link"
  },
  "durationSeconds": {
    "label": "Duration (s)",
    "format": "number"
  },
  "minutesBilled": {
    "label": "Minutes billed",
    "format": "number"
  },
  "language": {
    "label": "Language",
    "format": "text"
  },
  "confidence": {
    "label": "Confidence",
    "format": "number"
  },
  "transcript": {
    "label": "Transcript",
    "format": "text"
  },
  "speakerTranscript": {
    "label": "Speakers",
    "format": "text"
  },
  "srt": {
    "label": "SRT",
    "format": "text"
  },
  "summary": {
    "label": "Summary",
    "format": "text"
  },
  "error": {
    "label": "Error",
    "format": "text"
  }
}
```

## About this Actor

This example demonstrates how to use [Audio Transcription - Deepgram Nova-3, SRT, Diarization](https://apify.com/kaz_kakyo/audio-transcriber) with a specific input configuration. Visit the [Actor detail page](https://apify.com/kaz_kakyo/audio-transcriber) to learn more, explore other use cases, and run it yourself.