# Podcast Transcription - RSS Feed to Text, SRT & VTT (`admirala/podcast-rss-transcriber`) Actor

Podcast transcription from any RSS feed with Whisper AI: newest episodes to full text plus SRT and VTT subtitles with timestamps. 99 languages, auto-detect. $0.0059 per audio minute.

- **URL**: https://apify.com/admirala/podcast-rss-transcriber.md
- **Developed by:** [Ja doei](https://apify.com/admirala) (community)
- **Categories:** AI, Videos
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.13 / 1,000 podcast transcription (whisper base), per 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

## Podcast Transcription - RSS Feed to Text, SRT & VTT

> ✅ **Tested daily** with its default input (Apify's automated QA plus our own smoke test before every release).

**Podcast transcription** straight from an RSS feed: paste one or more **podcast RSS feed URLs** and this Actor transcribes the newest episodes with **Whisper AI speech recognition**. Each episode comes back with the full transcript, **SRT** and **VTT** subtitles with timestamps and the episode metadata, for **$0.0059 per audio minute** (under a cent).

### How it works

1. Reads the RSS feed and sorts episodes newest first.
2. Takes the audio file the publisher lists for each episode (the `<enclosure>` in the feed).
3. Transcribes it with Whisper (`base` for speed, `small` for higher accuracy). 99 languages, automatic language detection.
4. Writes one dataset row per episode.

### Input

| Field | Description |
|---|---|
| `feedUrls` | Public podcast RSS feed URLs (not Spotify/Apple/YouTube page links). The audio file in each episode's <enclosure> is transcribed. Example: \["https://feeds.npr.org/500005/podcast.xml"]. |
| `maxEpisodes` | Number of episodes per feed, newest first. Cost scales with total audio minutes, so start with 1. |
| `model` | Whisper model: base = fast, $0.0059 per audio minute; small = more accurate, $0.0155 per audio minute. |
| `language` | Optional ISO 639-1 code of the spoken language, e.g. 'en', 'de', 'nl'. Empty = auto-detect. |
| `maxMinutesPerEpisode` | Transcribe only the first N minutes of each episode (0 = whole episode). You pay only for the minutes transcribed, so this caps cost per episode. |

### Output (one row per episode)

```json
{
  "feed_title": "NPR News Now",
  "episode_title": "1pm ET, October 23 | The latest headlines from NPR",
  "pub_date": "Fri, 23 Oct 2026 17:34:40 +0000",
  "audio_url": "https://.../default.mp3",
  "duration_s": 317.7,
  "language": "en",
  "text": "This is NPR News Now. The latest headlines every hour ...",
  "srt": "1\n00:00:00,000 --> 00:00:04,400\nThis is NPR News Now.\n...",
  "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:04.400\n...",
  "model": "base",
  "billed_minutes": 6
}
```

### Pricing (pay per event)

| Event | Price |
|---|---|
| Transcription with Whisper base | $0.0059 per audio minute |
| Premium transcription with Whisper small | $0.0155 per audio minute |

Billing is per started minute of audio that was actually transcribed (with `maxMinutesPerEpisode` you pay only for the capped part). Episodes that fail to download or transcribe are not charged. Higher Apify plans get lower prices.

### Use cases

- Searchable archives and show notes for podcasters
- Subtitles for audiograms and video clips
- Monitoring what is said in industry or news podcasts
- Feeding podcast content into search, summaries or LLM pipelines

### Notes

- Only the audio files published in the RSS feed are used. Pages of video or streaming platforms (YouTube, Spotify, SoundCloud ...) are not supported.
- Make sure your use of the transcripts respects the podcast's copyright and terms.
- Speech recognition: Whisper (OpenAI, MIT license) via faster-whisper.

### Use with AI agents (MCP)

This Actor can be used as a tool by AI agents (Claude, Cursor, VS Code, other MCP clients) through the official [Apify MCP server](https://docs.apify.com/platform/integrations/mcp):

- Add only this Actor as a tool: `https://mcp.apify.com?tools=admirala/podcast-rss-transcriber` (sign in with OAuth or an Apify API token).
- Or connect `https://mcp.apify.com` and let the agent find it with `search-actors` (e.g. "podcast transcription"), read the input schema with `fetch-actor-details` and run it with `call-actor`.

Example input an agent can pass:

```json
{
  "feedUrls": [
    "https://feeds.npr.org/500005/podcast.xml"
  ],
  "maxEpisodes": 1,
  "model": "base"
}
```

Cost per call: $0.0059 per transcribed audio minute (base) or $0.0155 (small). Use `maxMinutesPerEpisode` to cap cost; failed episodes are free. Results come back as dataset items (`get-dataset-items`).

### FAQ

**How do I transcribe a podcast episode to text?**
Paste the show's RSS feed in `feedUrls` and set `maxEpisodes`. The audio file listed in the feed is transcribed with Whisper.

**How much does podcast transcription cost?**
$0.0059 per audio minute with the base model, so a 30-minute episode is about $0.18. The small model costs $0.0155 per minute.

**Can I get SRT or VTT subtitles for a podcast?**
Yes, every episode row includes `srt` and `vtt` with timestamps besides the plain `text`.

**Does it work with Spotify or YouTube podcast links?**
No, only public RSS feeds and the audio files they publish.

### Related actors

- RSS Feed Reader - RSS & Atom to JSON (bulk, auto-discovery) (coming soon to Apify Store)
- [YouTube Transcript & Audio to Text (Whisper) - SRT/VTT](https://apify.com/admirala/audio-to-subtitles)
- YouTube Transcript Scraper - Text, Timestamps & SRT (coming soon to Apify Store)

### More examples

Ready-to-run Python, curl and MCP examples with real sample output: https://github.com/AdmiraalA/apify-scrapers-examples

# Actor input Schema

## `feedUrls` (type: `array`):

Public podcast RSS feed URLs (not Spotify/Apple/YouTube page links). The audio file in each episode's <enclosure> is transcribed. Example: \["https://feeds.npr.org/500005/podcast.xml"].

## `maxEpisodes` (type: `integer`):

Number of episodes per feed, newest first. Cost scales with total audio minutes, so start with 1.

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

Whisper model: base = fast, $0.0059 per audio minute; small = more accurate, $0.0155 per audio minute.

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

Optional ISO 639-1 code of the spoken language, e.g. 'en', 'de', 'nl'. Empty = auto-detect.

## `maxMinutesPerEpisode` (type: `integer`):

Transcribe only the first N minutes of each episode (0 = whole episode). You pay only for the minutes transcribed, so this caps cost per episode.

## Actor input object example

```json
{
  "feedUrls": [
    "https://feeds.npr.org/500005/podcast.xml"
  ],
  "maxEpisodes": 1,
  "model": "base",
  "maxMinutesPerEpisode": 0
}
```

# Actor output Schema

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

No description

# 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 = {
    "feedUrls": [
        "https://feeds.npr.org/500005/podcast.xml"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("admirala/podcast-rss-transcriber").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 = { "feedUrls": ["https://feeds.npr.org/500005/podcast.xml"] }

# Run the Actor and wait for it to finish
run = client.actor("admirala/podcast-rss-transcriber").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 '{
  "feedUrls": [
    "https://feeds.npr.org/500005/podcast.xml"
  ]
}' |
apify call admirala/podcast-rss-transcriber --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,admirala/podcast-rss-transcriber"
        }
    }
}
```

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/yCoVP0Bol0wgO9Yxs/builds/YMgu0ZGkSLWlTNffG/openapi.json