# Podcast & Audio RSS Transcript Extractor (`pulse_extract/podcast-transcript-extractor`) Actor

Extract timestamped transcripts (plain text, SRT, Markdown, segments) from Apple Podcasts, Spotify links, RSS feeds, or direct audio URLs using native Podcasting 2.0 transcripts and faster-whisper AI.

- **URL**: https://apify.com/pulse_extract/podcast-transcript-extractor.md
- **Developed by:** [Pulse Extract](https://apify.com/pulse_extract) (community)
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.00 / 1,000 episode transcript returneds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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 & Audio RSS Transcript Extractor

Extract clean, timestamped transcripts (**plain text**, **SRT subtitles**, **LLM-ready Markdown**, and **raw timecoded segments**) from **Apple Podcasts**, **Spotify podcast links**, **RSS feeds**, **direct MP3/M4A/WAV URLs**, or plain show names — with zero proxies and zero browser overhead.

Uses **instant Podcasting 2.0 native `<podcast:transcript>` files** when available (saving compute and `audio-minute` costs), and automatically falls back to **`faster-whisper` AI** (int8 CPU + Voice Activity Detection) when a show does not publish a native transcript.

***

### Key Features

- **Universal Input Support:** Pass Apple Podcasts show or `?i=` episode links, Spotify show/episode links, raw XML RSS feed URLs, direct audio file URLs, or simply a show name (`"NPR News Now"`).
- **Hybrid Native + Whisper Pipeline:** Automatically checks for official Podcasting 2.0 `<podcast:transcript>` (WebVTT, SRT, JSON, or TXT) first — and seamlessly transcribes audio with `faster-whisper` when none is provided.
- **4 Output Formats in One Run:** Clean `transcriptText`, standard `transcriptSrt`, timestamped `[MM:SS]` `transcriptMarkdown` grouped for RAG/LLMs, and granular `segments[]` (`start`, `end`, `text`).
- **Pre-Transcription Filtering:** Filter by `episodeKeywords` and `publishedWithinDays` *before* downloading audio or running Whisper so you never pay for irrelevant episodes.
- **Optional Preview Trimming:** Set `maxTranscribeSeconds` (e.g., `60`) to inspect the intro of long podcasts quickly before running full episodes.

***

### Supported Input Formats

| Source Type | Example Input |
| :--- | :--- |
| **RSS Feed URL** | `https://podnews.net/rss` or `https://feeds.npr.org/500005/podcast.xml` |
| **Apple Podcasts (Show or Episode)** | `https://podcasts.apple.com/us/podcast/lex-fridman-podcast/id1434243584` |
| **Spotify (Show or Episode)** | `https://open.spotify.com/show/2MAi0BvDc6GTFvKFPXnkCL` |
| **Direct Audio URL** | `https://example.com/audio/interview.mp3` |
| **Podcast Search Query** | `NPR News Now` |

***

### Example Input

```json
{
  "sources": [
    "https://podnews.net/rss",
    "https://feeds.npr.org/500005/podcast.xml"
  ],
  "maxEpisodesPerShow": 2,
  "episodeKeywords": [],
  "publishedWithinDays": 14,
  "preferNativeTranscript": true,
  "whisperModel": "base",
  "language": "",
  "maxAudioMinutes": 180,
  "maxTranscribeSeconds": 0,
  "includeSrt": true,
  "includeMarkdown": true,
  "includeSegments": true
}
```

***

### Example Output Item

```json
{
  "sourceInput": "https://podnews.net/rss",
  "showTitle": "Podnews Daily",
  "showAuthor": "Podnews",
  "feedUrl": "https://podnews.net/rss",
  "episodeGuid": "podnews-2026-11-18",
  "episodeTitle": "Episode Title",
  "publishedAt": "2026-11-18T06:00:00+00:00",
  "durationSeconds": 208,
  "audioUrl": "https://...",
  "episodeUrl": "https://podnews.net/update/...",
  "transcriptSource": "native_rss",
  "detectedLanguage": "en",
  "languageProbability": null,
  "audioMinutesBilled": 0,
  "wordCount": 512,
  "transcriptText": "Welcome to Podnews Daily...",
  "transcriptSrt": "1\n00:00:00,000 --> 00:00:04,200\nWelcome to Podnews Daily...",
  "transcriptMarkdown": "# Episode Title\n\n*Podcast: Podnews Daily*\n\n**[00:00]** Welcome to Podnews Daily...",
  "segments": [
    { "start": 0.0, "end": 4.2, "text": "Welcome to Podnews Daily..." }
  ],
  "scrapedAt": "2026-11-19T03:15:00+00:00"
}
```

***

### Pricing & Billing Transparency

This Actor uses fair **Pay-Per-Event (PPE)** billing:

- **Actor Start:** `$0.00005` per run.
- **Per Episode Returned (`episode-processed`):** `$0.002` per episode.
- **Per Audio Minute Transcribed via Whisper (`audio-minute`):** `$0.003` per started minute — **charged ONLY when `transcriptSource` is `"whisper"`** (`$0` audio-minute charge when a native RSS transcript is used!).

***

### Use Cases & Integrations

- **AI Knowledge Bases & RAG Pipelines:** Feed timestamped `transcriptMarkdown` directly into Pinecone, Qdrant, Supabase Vector, or LangChain via **n8n** / **Make**.
- **Content Repurposing & Newsletters:** Schedule daily RSS extraction to summarize competitor or industry podcasts automatically into newsletter briefs, blog posts, or short-form clips.
- **AI Agents & MCP:** Connect through Apify's MCP server so Claude or Cursor can search and read recent podcast episodes cleanly.

***

### FAQ

**How do Spotify links work without scraping Spotify audio DRM?**\
Spotify show and episode URLs are resolved via Spotify's public `oembed` metadata endpoint and matched against Apple's open podcast directory to locate the publisher's official open RSS audio feed. (Spotify-exclusive shows without a public RSS feed cannot be resolved.)

**How do I save costs on long 2-hour episodes?**\
Keep `preferNativeTranscript: true` (zero Whisper cost whenever feeds publish `<podcast:transcript>`), use `episodeKeywords` to filter before transcribing, or set `maxTranscribeSeconds` during testing.

# Actor input Schema

## `sources` (type: `array`):

Accepts RSS feed URLs, Apple Podcasts show/episode URLs (podcasts.apple.com/.../id...), Spotify show/episode URLs (open.spotify.com/...), direct audio URLs (.mp3/.m4a/.wav), or plain show search queries.

## `maxEpisodesPerShow` (type: `integer`):

Maximum newest episodes to extract per show (ignored when targeting a specific single episode URL or direct audio file).

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

Keep episodes matching at least one keyword (case-insensitive) in the episode title or show notes.

## `publishedWithinDays` (type: `integer`):

Keep only episodes published within the last N days. Set to 0 to disable date filtering.

## `preferNativeTranscript` (type: `boolean`):

Use official Podcasting 2.0 <podcast:transcript> files (VTT/SRT/JSON/TXT) immediately when present in the RSS feed, skipping audio download and audio-minute charges.

## `whisperModel` (type: `string`):

Model used when audio transcription is needed. 'base' offers the best balance of speed and accuracy; 'tiny' is fastest.

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

Optional two-letter language hint (e.g. 'en', 'fr', 'es', 'de') to speed up Whisper. Leave blank for automatic language detection.

## `maxAudioMinutes` (type: `integer`):

Safety limit to skip extraordinarily long episodes before downloading. Set to 0 for no limit.

## `maxTranscribeSeconds` (type: `integer`):

If > 0, trims downloaded audio via ffmpeg to the first N seconds before running Whisper (useful for quick previews/tests). Set to 0 to transcribe full episodes.

## `includeSrt` (type: `boolean`):

Include formatted .srt subtitle text in each dataset item.

## `includeMarkdown` (type: `boolean`):

Include LLM/RAG-ready timestamped Markdown transcript.

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

Include raw \[{start, end, text}] segment objects.

## Actor input object example

```json
{
  "sources": [
    "https://podnews.net/rss"
  ],
  "maxEpisodesPerShow": 1,
  "episodeKeywords": [],
  "publishedWithinDays": 0,
  "preferNativeTranscript": true,
  "whisperModel": "base",
  "language": "",
  "maxAudioMinutes": 180,
  "maxTranscribeSeconds": 0,
  "includeSrt": true,
  "includeMarkdown": true,
  "includeSegments": true
}
```

# 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 = {
    "sources": [
        "https://podnews.net/rss"
    ],
    "maxEpisodesPerShow": 1
};

// Run the Actor and wait for it to finish
const run = await client.actor("pulse_extract/podcast-transcript-extractor").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 = {
    "sources": ["https://podnews.net/rss"],
    "maxEpisodesPerShow": 1,
}

# Run the Actor and wait for it to finish
run = client.actor("pulse_extract/podcast-transcript-extractor").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 '{
  "sources": [
    "https://podnews.net/rss"
  ],
  "maxEpisodesPerShow": 1
}' |
apify call pulse_extract/podcast-transcript-extractor --silent --output-dataset

```

## MCP server setup

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

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/eHRdXI2rkHcnPbbSk/builds/G5Sy7nHQoGgxNl93F/openapi.json
