# Split recordings into RAG chunks with timestamps

**Use case:** 

Transcribe a podcast, meeting or lecture and get it back as RAG-ready chunks of about 1,500 characters, made of whole sentences, each with its start and end time. Store the chunks in a vector database and every search hit can link to the right moment of the recording. Whisper on CPU, $5 per 1,000 audio minutes.

## Input

```json
{
  "urls": [
    "https://archive.org/download/short_story_036_0904_librivox/shortstory036_sciencevsluck_gam_64kb.mp3"
  ],
  "episodesPerFeed": 1,
  "model": "base",
  "language": "auto",
  "task": "transcribe",
  "wordTimestamps": false,
  "maxMinutesPerFile": 180,
  "chunkSize": 1500,
  "chunkOverlap": 200,
  "saveFiles": true,
  "maxFileSizeMb": 500,
  "requestHeaders": {}
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "link"
  },
  "fileName": {
    "label": "File"
  },
  "episodeTitle": {
    "label": "Episode"
  },
  "language": {
    "label": "Language"
  },
  "durationSec": {
    "label": "Duration (s)",
    "format": "number"
  },
  "billedMinutes": {
    "label": "Billed minutes",
    "format": "number"
  },
  "wordCount": {
    "label": "Words",
    "format": "number"
  },
  "text": {
    "label": "Transcript"
  },
  "error": {
    "label": "Error"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The Audio to Text — Whisper Transcription, SRT, RAG Chunks Actor is ready to run with the inputs already set for "Split recordings into RAG chunks with timestamps". [Sign up or log in](https://console.apify.com/create-task-from-example/49eOJC46Rtdjf0WaT) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Split recordings into RAG chunks with timestamps" task

The Audio to Text — Whisper Transcription, SRT, RAG Chunks Actor will start running based on the input automatically. You can also change all the input fields, like audio or video links, episodes per feed, and more, to match your specific use case.

### 3. Receive the "Split recordings into RAG chunks with timestamps" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as URL, file, episode, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Split recordings into RAG chunks with timestamps" task via API](https://apify.com/saliga/audio-to-text.md).

## About this Actor

This example demonstrates how to use [Audio to Text — Whisper Transcription, SRT, RAG Chunks](https://apify.com/saliga/audio-to-text.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/saliga/audio-to-text.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/saliga/audio-to-text.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).