# Audio Transcription: Speech to Text, Video, Podcast | $0.01/min (`v0iddo/audio-transcription`) Actor

Speech to text with Whisper: transcribe audio and video files and podcast episodes, with timestamps and SRT or VTT subtitles. Paste MP3, M4A, WAV, MP4 or other media links, or podcast RSS feeds for their newest episodes. About 100 languages, detected on their own, and translation to English.

- **URL**: https://apify.com/v0iddo/audio-transcription.md
- **Developed by:** [vøiddo](https://apify.com/v0iddo) (community)
- **Categories:** Videos, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $7.00 / 1,000 audio minutes

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

## Audio Transcription: Speech to Text, Video, Podcast | $0.01/min

Speech to text with Whisper: transcribe audio and video files and podcast episodes, with timestamps and SRT or VTT subtitles. Paste MP3, M4A, WAV, MP4 or other media links, or podcast RSS feeds for their newest episodes. About 100 languages, detected on their own, and translation to English.

- Pay per minute of audio transcribed (the price is on the Pricing tab): the platform usage of the run is included, and a file that fails is not charged.
- No login, no cookies, no account on the podcast or file host: public audio and video files and podcast feeds only.
- Export to JSON, CSV, Excel, XML or HTML, or read the rows through the Apify API.
- Start it from the Console, on a schedule, through the API, or as a tool for agents over MCP.
- Tested every day on its example input, with the rows checked, and repaired when a check fails.

### What you can use it for

- Podcast research and show notes: the full text of the newest episodes of a public feed, with title and date.
- Subtitles: SRT and WebVTT text with timestamps for a talk, lesson or video you host at a public link.
- Content reuse: turn interviews, webinars and lectures into text you can quote, search and summarise.
- Media monitoring: on a schedule, transcribe the new episodes whose title holds your keywords.
- English versions: speech in another language returned as English text in the same run.

### What you get

Every result is one row in the run's dataset. Download it as JSON, CSV, Excel or HTML, or read it through the Apify API. The main fields:

| Field | Meaning |
|---|---|
| `fileName` | File |
| `episodeTitle` | Episode |
| `language` | Language |
| `durationSeconds` | Length (s) |
| `billedMinutes` | Minutes charged |
| `wordCount` | Words |
| `text` | Transcript |
| `mediaUrl` | Media |

Example row:

```json
{
  "source": "url",
  "mediaUrl": "https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg",
  "fileName": "Jfk_rice_university_we_choose_to_go_to_the_moon.ogg",
  "contentType": "application/ogg",
  "fileBytes": 17193282,
  "podcastTitle": null,
  "podcastFeed": null,
  "episodeTitle": null,
  "episodeUrl": null,
  "publishedAt": null,
  "durationSeconds": 1060.4,
  "transcribedSeconds": 60.0,
  "truncated": true,
  "language": "en",
  "languageProbability": 0.96,
  "task": "transcribe",
  "model": "base",
  "text": "We meet at a college noted for knowledge in a city noted for progress in a state noted for strength and we stand in need of all three.",
  "wordCount": 27,
  "segments": [
    {
      "start": 48.2,
      "end": 55.9,
      "text": "We meet at a college noted for knowledge in a city noted for progress in a state noted for strength"
    },
    {
      "start": 55.9,
      "end": 58.3,
      "text": "and we stand in need of all three."
    }
  ],
  "srt": null,
  "vtt": null,
  "billedMinutes": 1,
  "processingSeconds": 6.1,
  "error": null,
  "transcribedAt": "2026-10-23T16:10:05Z"
}
```

### How to use it

1. Open the **Input** tab (or call the actor through the API, see below).
2. Fill in **Audio or video links**, **Maximum minutes per file**; the form opens with a working example.
3. Set **Maximum results** to cap the size and the cost of the run.
4. Click **Start**. Rows appear on the **Output** tab while the run works.
5. Download the dataset, or connect it to Google Sheets, Make, Zapier, n8n or a webhook.

### Input

| Field | Type | Required | Description |
|---|---|---|---|
| `mediaUrls` | array | no | Direct links to media files: MP3, M4A, AAC, WAV, OGG, OPUS, FLAC, MP4, MOV, WEBM and more. Video files are transcribed from their sound track. Links to web pages (a YouTube or Spotify page) are not files and are refused. |
| `podcastFeeds` | array | no | RSS feed links of podcasts. The newest episodes of each feed are transcribed (see Episodes per feed). The feed link is on the show's website or its hosting page; Apple Podcasts and Spotify pages are not feeds. |
| `episodesPerFeed` | integer | no | How many of each feed's newest episodes to transcribe. Default: `1`. |
| `episodeKeywords` | array | no | Keep only feed episodes whose title holds one of these words. Leave empty for the newest episodes. |
| `language` | select | no | The language spoken in the files. Detected from the first 30 seconds when left on Detect automatically; set it when the start is music or silence. Default: `"auto"`. |
| `task` | select | no | Write the text in the spoken language, or translate it to English. Allowed: transcribe, translate. Default: `"transcribe"`. |
| `model` | select | no | Speech recognition model. Small is better with accents, noise and languages other than English, takes about twice as long and is charged as two minutes per minute. Allowed: base, small. Default: `"base"`. |
| `maxMinutesPerFile` | integer | no | Only the first this many minutes of each file are transcribed and charged; the row says when a file was cut. Default: `120`. |
| `includeSegments` | boolean | no | Return the transcript also as segments with start and end seconds. Default: `true`. |
| `includeSubtitles` | boolean | no | Return the transcript also as SRT and WebVTT subtitle text. Default: `false`. |
| `maxItems` | integer | no | The run stops after this many result rows. It also caps what one run can cost. Default: `100`. |
| `proxyConfiguration` | object | no | Leave as is: the run starts on the cheapest network the site accepts and switches to Apify Proxy automatically when the site blocks it. Pick proxy groups here only to force one specific network. |

Example input:

```json
{
  "mediaUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"
  ],
  "maxMinutesPerFile": 8,
  "maxItems": 1
}
```

### Pricing

You pay per started minute of audio transcribed, at the price per minute on the Pricing tab (a 30 second clip counts as one minute; with the small model each minute counts twice). Rows themselves are not charged, and a file that fails costs nothing. Set **Maximum minutes per file** and **Maximum results** to cap what a run can cost; the run also stops at your spending limit.

### Limits and notes

- One row per file: the whole text, its language, the length of the file, the minutes transcribed and, when asked, timestamped segments and SRT / VTT subtitles. Podcast rows add the show, the episode title, its date and its page.
- Speed: about 6 minutes of audio per minute of run time with the base model at the default 4 GB of memory (8 GB is about twice as fast at the same price per minute). Long files fit in one run up to the run's time limit; raise Timeout for many hours of audio.
- Silence and music are skipped before recognition, so a long intro does not produce made up text; the minutes charged are the minutes of the file that were processed.
- Files are fetched only from addresses whose robots.txt allows it, and not from hosts that close their content to machine learning agents in robots.txt (several large podcast hosts do). Such a file comes back as a row with the reason, at no charge.
- Links to web pages are not media files: download links of files, or podcast feeds, are needed. Files up to 1.5 GB.
- The files are processed in the run's own container and deleted with it; nothing is sent to another service.
- Only publicly visible data is collected. No login, no paywalled content, no personal contact details.
- The actor reads only pages that the site's robots.txt leaves open to automated access.
- Sites change their pages from time to time. The actor is checked automatically and repaired when a check fails.
- Each run sends one short usage record to the developer: the Actor and run IDs, the number of results, whether the run succeeded (and if not, the kind of error, such as "blocked" or "input problem"), whether the account is on a paid Apify plan, how the run was started (for example from the Console, the API or a schedule) and a one-way fingerprint of the account (a hash, not the account ID), so that repeat runs of one account count once. It contains nothing from your input or results.

### Run it through the API

Python, with the `apify-client` package:

```python
from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("v0iddo/audio-transcription").call(run_input={"mediaUrls": ["https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"], "maxMinutesPerFile": 8, "maxItems": 1})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)
```

JavaScript, with the `apify-client` package:

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

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('v0iddo/audio-transcription').call({"mediaUrls": ["https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"], "maxMinutesPerFile": 8, "maxItems": 1});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);
```

One HTTP call that waits for the run and returns the rows (for runs that finish within 5 minutes):

```bash
curl -X POST "https://api.apify.com/v2/acts/v0iddo~audio-transcription/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"mediaUrls": ["https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"], "maxMinutesPerFile": 8, "maxItems": 1}'
```

### Use it from an agent (MCP)

Claude, Cursor, VS Code and other MCP clients can call this actor as a tool through the Apify MCP server. Add it to the client's MCP configuration:

```json
{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=v0iddo/audio-transcription",
      "headers": {
        "Authorization": "Bearer <YOUR_APIFY_TOKEN>"
      }
    }
  }
}
```

Then ask, for example: "Transcribe the two newest episodes of this podcast feed and give me the text with timestamps."

### FAQ

#### Do I need an account on the podcast or file host, cookies or an API key?

No. The actor reads only what every visitor of the podcast or file host can see, without logging in. You only need an Apify account to start it.

#### How many results can one run return?

Up to 1,000 rows per run. Without a limit it stops at 100. Set **Maximum results** to the number you need; large jobs can also be split into several runs or scheduled.

#### How am I charged?

Per started minute of audio transcribed, at the price on the Pricing tab for your Apify plan; the small model counts each minute twice. The platform usage of the run is included in that price. A file that fails costs nothing. When the run reaches your spending limit, it cuts the current file short at the last minute you can pay for and stops.

#### Why did my run return no results?

The status message of the run says why: nothing matched the input, the input was not a page the actor understands, the page is closed to automated access by robots.txt, or the site refused every network the actor tried. Check the input against the example above and run it again with a small limit.

#### Can I run it on a schedule?

Yes. Save your input as a task and add a schedule in the Apify Console (daily, hourly or with a cron expression). Each run gets its own dataset, so you keep a history.

#### Which formats can I export?

JSON, CSV, Excel, XML, HTML table and RSS from the Output tab or the API. Integrations send the rows to Google Sheets, Slack, Make, Zapier, n8n or a webhook.

#### Is collecting this data allowed?

The actor collects only what the podcast or file host publishes to every visitor, without a login, and it reads only pages that robots.txt leaves open. Public data can still be personal data under laws such as the GDPR, and sites have their own terms: make sure your use of the data follows the rules that apply to you.

#### What happens when the podcast or file host changes its pages?

Automated tests run the actor every day on the example input and check the rows, not only that the run finished. When a check fails, the actor is repaired and rebuilt; the build history on this page shows each update.

#### Something is missing or wrong. Where do I report it?

Open an issue on the Issues tab of this actor with the run link. Requests for a new field are welcome too.

### Related actors

- [Video Frame Extractor: Scenes, Thumbnails / $1.50 per 1,000](https://apify.com/v0iddo/video-frame-extractor)

# Actor input Schema

## `mediaUrls` (type: `array`):

Direct links to media files: MP3, M4A, AAC, WAV, OGG, OPUS, FLAC, MP4, MOV, WEBM and more. Video files are transcribed from their sound track. Links to web pages (a YouTube or Spotify page) are not files and are refused.

## `podcastFeeds` (type: `array`):

RSS feed links of podcasts. The newest episodes of each feed are transcribed (see Episodes per feed). The feed link is on the show's website or its hosting page; Apple Podcasts and Spotify pages are not feeds.

## `episodesPerFeed` (type: `integer`):

How many of each feed's newest episodes to transcribe.

## `episodeKeywords` (type: `array`):

Keep only feed episodes whose title holds one of these words. Leave empty for the newest episodes.

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

The language spoken in the files. Detected from the first 30 seconds when left on Detect automatically; set it when the start is music or silence.

## `task` (type: `string`):

Write the text in the spoken language, or translate it to English.

## `model` (type: `string`):

Speech recognition model. Small is better with accents, noise and languages other than English, takes about twice as long and is charged as two minutes per minute.

## `maxMinutesPerFile` (type: `integer`):

Only the first this many minutes of each file are transcribed and charged; the row says when a file was cut.

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

Return the transcript also as segments with start and end seconds.

## `includeSubtitles` (type: `boolean`):

Return the transcript also as SRT and WebVTT subtitle text.

## `maxItems` (type: `integer`):

The run stops after this many result rows. It also caps what one run can cost.

## `proxyConfiguration` (type: `object`):

Leave as is: the run starts on the cheapest network the site accepts and switches to Apify Proxy automatically when the site blocks it. Pick proxy groups here only to force one specific network.

## Actor input object example

```json
{
  "mediaUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"
  ],
  "episodesPerFeed": 1,
  "language": "auto",
  "task": "transcribe",
  "model": "base",
  "maxMinutesPerFile": 8,
  "includeSegments": true,
  "includeSubtitles": false,
  "maxItems": 1,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

# Actor output Schema

## `results` (type: `string`):

One dataset row per processed item.

# 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 = {
    "mediaUrls": [
        "https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"
    ],
    "maxMinutesPerFile": 8,
    "maxItems": 1,
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("v0iddo/audio-transcription").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 = {
    "mediaUrls": ["https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"],
    "maxMinutesPerFile": 8,
    "maxItems": 1,
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("v0iddo/audio-transcription").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 '{
  "mediaUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/5/50/Jfk_rice_university_we_choose_to_go_to_the_moon.ogg"
  ],
  "maxMinutesPerFile": 8,
  "maxItems": 1,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call v0iddo/audio-transcription --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,v0iddo/audio-transcription"
        }
    }
}
```

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/UhD5lVg0o3FDVvi6d/builds/VcE4lDEdjB2fzlayV/openapi.json