# Transcribe Audio in ChatGPT via MCP

**Use case:** 

Configure Apify MCP in a compatible ChatGPT workspace and authenticate first. This Task runs a speech-demo preset; it does not connect ChatGPT. The $0.10 cap is for this demo; adjust budget and timeout for your audio. Guide: https://api.apify.com/v2/key-value-stores/Vvn9WrUtmu3VyWGMW/records/tasks.html?attachment=true#chatgpt

## Input

```json
{
  "urls": [
    "https://storage.googleapis.com/cloud-samples-data/speech/commercial_mono.wav"
  ],
  "exportRag": false,
  "timestamps": "segment",
  "diarize": false,
  "startTime": 0,
  "summarize": false,
  "chapters": false,
  "actionItems": false,
  "extractKeywords": false,
  "maxItemsPerSource": 20,
  "maxItems": 100,
  "skipPreviouslyProcessed": false
}
```

## Output

```json
{
  "url": {
    "label": "Source URL",
    "format": "string"
  },
  "text": {
    "label": "Transcript",
    "format": "string"
  },
  "paragraphs": {
    "label": "Paragraphs",
    "format": "array"
  },
  "no_speech": {
    "label": "No speech detected",
    "format": "boolean"
  },
  "result_record_key": {
    "label": "Full result record",
    "format": "string"
  },
  "language": {
    "label": "Detected language",
    "format": "string"
  },
  "duration_s": {
    "label": "Duration (seconds)",
    "format": "number"
  },
  "engine": {
    "label": "Engine",
    "format": "string"
  },
  "speaker_scope": {
    "label": "Speaker identity scope",
    "format": "string"
  },
  "usage.minutes": {
    "label": "Calculated minutes",
    "format": "number"
  },
  "usage.diarized": {
    "label": "Diarized",
    "format": "boolean"
  },
  "billing.status": {
    "label": "Payment status",
    "format": "string"
  },
  "billing.stop": {
    "label": "Billing stopped",
    "format": "boolean"
  },
  "stop_processing": {
    "label": "Processing stopped",
    "format": "boolean"
  },
  "artifact_errors": {
    "label": "Unavailable downloads",
    "format": "array"
  },
  "error": {
    "label": "Error",
    "format": "string"
  }
}
```

## How it works

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

The Audio & Video Transcriber — Speech to Text API Actor is ready to run with the inputs already set for "Transcribe Audio in ChatGPT via MCP". [Sign up or log in](https://console.apify.com/create-task-from-example/tQy2FuCDZAaboazCw) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Transcribe Audio in ChatGPT via MCP" task

The Audio & Video Transcriber — Speech to Text API Actor will start running based on the input automatically. You can also change all the input fields, like audio / video urls, export rag passages (jsonl), and more, to match your specific use case.

### 3. Receive the "Transcribe Audio in ChatGPT via MCP" 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 source url, transcript, paragraphs, 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 "Transcribe Audio in ChatGPT via MCP" task via API](https://apify.com/andronixmd/speech-to-text-transcriber.md).

## About this Actor

This example demonstrates how to use [Audio & Video Transcriber — Speech to Text API](https://apify.com/andronixmd/speech-to-text-transcriber.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/andronixmd/speech-to-text-transcriber.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/andronixmd/speech-to-text-transcriber.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`).