# Audio to Text Transcription: MP3, WAV & M4A Speech to Text (`aemon/audio-file-to-text`) Actor

Transcribe audio files from a link into text: MP3, WAV, M4A, FLAC, OGG and MP4. Get the full transcript with timestamps and optional SRT or VTT subtitles as JSON, CSV or Excel. Whisper AI, 90+ languages, $0.004 per minute, failed files are free.

- **URL**: https://apify.com/aemon/audio-file-to-text.md
- **Developed by:** [Aemon](https://apify.com/aemon) (community)
- **Categories:** AI, Automation, Developer tools
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $3.25 / 1,000 minute of transcribed audios

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

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 examples already wired to this Actor's own input schema, see the [API](#api) section below.

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`).

# README

### What does Audio File to Text do?

**Audio File to Text** turns audio files into text. Paste links to **MP3, WAV, M4A, FLAC, OGG** or **MP4** files and get the full transcript, timestamped segments, the detected language and optional **SRT or VTT subtitles**, one row per file, as JSON, CSV or Excel. It uses Whisper large-v3-turbo, works in **90+ languages** and needs no account anywhere except Apify.

- 💸 **$0.004 per minute of audio**, about **$0.24 per hour**, platform usage included. Files that fail are **free**.
- 🎧 **Any common format**: MP3, M4A, AAC, WAV, FLAC, OGG, OPUS, MP4, MOV and WEBM from any public link (cloud storage, a CDN, your own server, a podcast host).
- 🌍 **90+ languages**, detected automatically, or pick the language yourself.
- ⏱️ **Long recordings are fine**: interviews, lectures and meetings of 2–3 hours are split and transcribed automatically.
- 📝 **Ready for AI**: clean text plus segments with start and end times, ready for ChatGPT, Claude, RAG pipelines, search and subtitles.
- 🔗 **Built for automation**: one HTTP request from n8n, Make or Zapier, or a tool for AI agents through the Apify MCP server.

### What you get

One row per file (real output for the prefilled example, empty fields left out):

```json
{
    "status": "ok",
    "episodeTitle": "jfk.flac",
    "audioUrl": "https://github.com/openai/whisper/raw/main/tests/jfk.flac",
    "durationSec": 11,
    "language": "en",
    "hasSpeech": true,
    "text": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
    "wordCount": 22,
    "segments": [
        { "start": 0, "end": 10.4, "text": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country." }
    ],
    "srt": "1\n00:00:00,000 --> 00:00:10,400\nAnd so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.\n",
    "inputUrl": "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
}
```

| Field | What it is |
|---|---|
| `text` | The whole transcript as one clean text |
| `segments` | Parts of the transcript with `start` and `end` in seconds |
| `srt` / `vtt` | Subtitle file, when you pick a subtitle format |
| `language` | Detected (or chosen) language code |
| `durationSec`, `wordCount` | Length of the audio and number of words |
| `hasSpeech` | `false` when the file is only music or silence |
| `episodeTitle`, `audioUrl`, `inputUrl` | File name and the link it came from |

The default view is a table with the transcripts; export it as JSON, CSV, Excel or HTML, or read it through the API.

### What can you use audio transcription for?

- **Interviews and research**: turn recorded interviews into text you can search, quote and code.
- **Meetings, lectures and webinars**: notes and searchable archives from recordings.
- **Voice notes and call recordings**: get the text into your CRM, Notion or a spreadsheet.
- **Subtitles**: SRT or VTT files for videos and courses.
- **AI pipelines**: feed transcripts into ChatGPT, Claude, LangChain or a vector database for summaries, Q\&A and RAG.

### How to convert an audio file to text

1. Click **Try for free** (the Apify free plan's $5 monthly credit transcribes about 20 hours of audio).
2. Paste one or more links into **Audio file URLs**. Each link must download the file directly.
3. Optionally pick the spoken language, timestamps and a subtitle format.
4. Click **Start** and download the transcripts.

### Ready-to-run examples

Each example opens a pre-filled setup that you can run in one click and save as your own task:

- [MP3 to Text: Transcribe MP3 Files from a URL](https://apify.com/aemon/audio-file-to-text/examples/mp3-to-text): Convert MP3 files to text: paste direct MP3 links and get the full transcript with timestamps and the detected language, one row per file, as JSON, CSV or Excel.
- [WAV to Text: Speech to Text for WAV Recordings](https://apify.com/aemon/audio-file-to-text/examples/wav-to-text-transcription): Transcribe WAV recordings such as interviews, voice notes and call recordings into text with timestamps.
- [Audio to SRT Subtitles: MP3, M4A, WAV & MP4 to SRT](https://apify.com/aemon/audio-file-to-text/examples/audio-to-srt-subtitles): Create SRT subtitles from audio or video files: MP3, M4A, WAV, FLAC or MP4 links in, a ready-to-use SRT file and the full transcript out.

### Pricing

You pay **$0.004 per started minute** of transcribed audio. Platform usage (compute and downloads) is included.

| Audio | Price |
|---|---|
| 1-minute voice note | $0.004 |
| 30-minute interview | $0.12 |
| 1-hour lecture | $0.24 |
| 100 hours of recordings | $24 |

- Files that cannot be downloaded or transcribed are **free** and reported with an error code.
- Use **Skip files longer than** and the run's **maximum cost** setting to stay in budget. The Actor never charges more than the limit you set.
- Apify Starter, Scale and Business plans get lower per-minute prices automatically.

### Input example

```json
{
    "urls": [
        "https://github.com/openai/whisper/raw/main/tests/jfk.flac",
        "https://example.com/recordings/interview.mp3"
    ],
    "language": "auto",
    "includeSegments": true,
    "subtitleFormat": "srt"
}
```

### Use it from code, AI agents and automations

#### Input example

```json
{
    "urls": [
        "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
    ],
    "includeSegments": true,
    "subtitleFormat": "srt"
}
```

#### JavaScript

```js
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('aemon/audio-file-to-text').call({"urls":["https://github.com/openai/whisper/raw/main/tests/jfk.flac"],"includeSegments":true,"subtitleFormat":"srt"});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);
```

#### Python

```python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("aemon/audio-file-to-text").call(run_input={"urls":["https://github.com/openai/whisper/raw/main/tests/jfk.flac"],"includeSegments":True,"subtitleFormat":"srt"})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)
```

#### AI agents (MCP): Claude, ChatGPT, Cursor

This Actor works as a tool in any MCP client through the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp). Add it to the MCP configuration of Claude Desktop, Claude Code, Cursor or VS Code, with your [Apify API token](https://docs.apify.com/platform/integrations/api#api-token):

```json
{
    "mcpServers": {
        "apify": {
            "url": "https://mcp.apify.com?tools=aemon/audio-file-to-text",
            "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
        }
    }
}
```

Then ask your agent in plain words, for example: *"Transcribe this MP3 into text with timestamps and give me the three main points: https://example.com/interview.mp3"*

Agents without an Apify account can still use it: the Actor accepts [agentic payments](https://docs.apify.com/agents/payments), so an agent can run it and pay per run with x402 (USDC) or a Skyfire token instead of an API token.

#### n8n, Make and Zapier

One HTTP request runs the Actor and returns the results, so it fits into any automation tool:

```
POST https://api.apify.com/v2/acts/aemon~audio-file-to-text/run-sync-get-dataset-items?timeout=300
Authorization: Bearer YOUR_APIFY_TOKEN
Content-Type: application/json

{"urls":["https://github.com/openai/whisper/raw/main/tests/jfk.flac"],"includeSegments":true,"subtitleFormat":"srt"}
```

In **n8n** use an *HTTP Request* node, in **Make** *HTTP → Make a request* and in **Zapier** *Webhooks by Zapier → Custom Request*. Every file comes back as one item, ready for Google Sheets, Notion, Slack or email. You can also connect integrations and webhooks directly in the **Integrations** tab.

#### Ask an AI assistant about this Actor

Open a ready-made question about this Actor in [ChatGPT](https://chatgpt.com/?q=Using%20the%20Apify%20Actor%20%22Audio%20to%20Text%20Transcription%3A%20MP3%2C%20WAV%20%26%20M4A%20Speech%20to%20Text%22%20\(https%3A%2F%2Fapify.com%2Faemon%2Faudio-file-to-text\)%2C%20show%20me%20how%20to%20transcribe%20MP3%2C%20WAV%20or%20M4A%20files%20from%20a%20URL%20into%20text%20with%20timestamps.%20Include%20the%20input%20JSON%2C%20the%20output%20fields%20and%20how%20to%20run%20it%20through%20the%20API%2C%20the%20Apify%20MCP%20server%20or%20n8n.), [Claude](https://claude.ai/new?q=Using%20the%20Apify%20Actor%20%22Audio%20to%20Text%20Transcription%3A%20MP3%2C%20WAV%20%26%20M4A%20Speech%20to%20Text%22%20\(https%3A%2F%2Fapify.com%2Faemon%2Faudio-file-to-text\)%2C%20show%20me%20how%20to%20transcribe%20MP3%2C%20WAV%20or%20M4A%20files%20from%20a%20URL%20into%20text%20with%20timestamps.%20Include%20the%20input%20JSON%2C%20the%20output%20fields%20and%20how%20to%20run%20it%20through%20the%20API%2C%20the%20Apify%20MCP%20server%20or%20n8n.) or [Perplexity](https://www.perplexity.ai/search?q=Using%20the%20Apify%20Actor%20%22Audio%20to%20Text%20Transcription%3A%20MP3%2C%20WAV%20%26%20M4A%20Speech%20to%20Text%22%20\(https%3A%2F%2Fapify.com%2Faemon%2Faudio-file-to-text\)%2C%20show%20me%20how%20to%20transcribe%20MP3%2C%20WAV%20or%20M4A%20files%20from%20a%20URL%20into%20text%20with%20timestamps.%20Include%20the%20input%20JSON%2C%20the%20output%20fields%20and%20how%20to%20run%20it%20through%20the%20API%2C%20the%20Apify%20MCP%20server%20or%20n8n.).

### Errors are free and explained

Every link you paste gets a row. If a file cannot be processed, the row has `"status": "error"`, an `errorCode` and a readable `error` message, and **it is not charged**:

| Error code | What it means |
|---|---|
| `UNAVAILABLE` | The link returned "not found" (HTTP 404 or 410). |
| `DOWNLOAD_FAILED` / `NETWORK` | The file could not be downloaded, for example because it needs a login. Temporary problems are retried automatically first. |
| `TOO_LARGE` | The file is bigger than 1.5 GB. |
| `TOO_LONG` | The audio is longer than *Skip files longer than*. |
| `UNSUPPORTED_URL` | The text is not a valid link. |

### FAQ

**Where do my files need to be?**
At a public link that downloads the file directly, such as cloud storage with a public link, a CDN, your own server or a podcast host. Files that need a login cannot be downloaded.

**How long can a file be?**
Up to 10 hours and 1.5 GB. Long recordings are split and transcribed in parts automatically.

**Which formats work?**
MP3, M4A, AAC, WAV, FLAC, OGG, OPUS, and the audio track of MP4, MOV, MKV and WEBM videos.

**How accurate is it?**
It uses Whisper large-v3-turbo, one of the most accurate open speech recognition models. It handles accents, background noise and technical vocabulary well.

**Does it identify speakers?**
Not yet: the transcript has timestamps but no speaker labels. Tell us in the Issues tab if you need speaker detection.

**Are my files stored?**
No. Each file is downloaded for the run, transcribed and deleted. Only the transcript is saved, in your own dataset.

**Can it transcribe podcasts or videos from websites?**
Yes: for Apple Podcasts, Spotify, RSS feeds and AI summaries use [Podcast to Text](https://apify.com/aemon/podcast-audio-to-text), and for Instagram, TikTok, X and Facebook videos use [Video to Text](https://apify.com/aemon/video-to-text-for-ai).

### More Actors by Aemon

- [Podcast to Text](https://apify.com/aemon/podcast-audio-to-text): Apple Podcasts, Spotify and RSS episodes to text with AI summaries, same $0.004 per minute
- [YouTube Transcript Scraper](https://apify.com/aemon/youtube-transcript-scraper): transcripts of YouTube videos, channels and searches, $0.002 per video
- [Video to Text](https://apify.com/aemon/video-to-text-for-ai): Instagram, TikTok, X and Facebook transcripts with Whisper AI

### Support

Found a file that does not work or need a feature? Open an issue in the **Issues** tab; issues are answered within a day. If the Actor saves you time, a rating on the Reviews tab helps others find it.

Built and maintained by [Aemon](https://apify.com/aemon).

# Changelog

This Actor's version history is a separate document: https://apify.com/aemon/audio-file-to-text/changelog.md

# Actor input Schema

## `urls` (type: `array`):

Public links that download an audio or video file directly: MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, MP4, MOV or WEBM, one per line. Files behind a login cannot be downloaded.

## `language` (type: `string`):

Language spoken in the files. Auto-detect works for 90+ languages; pick a language only if detection gets it wrong. This is not a translation option.

## `includeSegments` (type: `boolean`):

Add a list of segments with start and end times in seconds.

## `subtitleFormat` (type: `string`):

Also return the transcript as a ready-to-use subtitle file.

## `maxDurationMinutes` (type: `integer`):

Longer files are skipped and not charged.

## `maxConcurrency` (type: `integer`):

How many files are processed at the same time.

## Actor input object example

```json
{
  "urls": [
    "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
  ],
  "language": "auto",
  "includeSegments": true,
  "subtitleFormat": "none",
  "maxDurationMinutes": 240,
  "maxConcurrency": 3
}
```

# Actor output Schema

## `transcripts` (type: `string`):

Transcript, language and word count for every file.

## `allFields` (type: `string`):

Complete items including timestamped segments and subtitles.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "urls": [
        "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("aemon/audio-file-to-text").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "urls": ["https://github.com/openai/whisper/raw/main/tests/jfk.flac"] }

# Run the Actor and wait for it to finish
run = client.actor("aemon/audio-file-to-text").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "urls": [
    "https://github.com/openai/whisper/raw/main/tests/jfk.flac"
  ]
}' |
apify call aemon/audio-file-to-text --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,aemon/audio-file-to-text"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/3xpwJCk6hWlgoPBPf/builds/JdiIWCbk3IVY8gSFs/openapi.json
