# Audio & Podcast Transcription API: Whisper, SRT & VTT (`steady-scrape/audio-podcast-transcription`) Actor

Transcribe audio and video file URLs, podcast RSS feeds and Apple Podcasts shows into timestamped text with the detected language, plus optional SRT/VTT subtitles. Monitor mode transcribes only new episodes. Pay per audio minute.

- **URL**: https://apify.com/steady-scrape/audio-podcast-transcription.md
- **Developed by:** [SteadyScrape](https://apify.com/steady-scrape) (community)
- **Categories:** AI, Videos
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.00 / 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.

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 & Podcast Transcription API: Whisper Transcripts, SRT & VTT

Turn audio and video files, podcast RSS feeds and Apple Podcasts shows into clean, timestamped transcripts. Paste file links or a feed, and get the full text, the detected language, timestamped segments and optional SRT or WebVTT subtitles, ready for show notes, SEO, search, research or RAG pipelines.

It uses the Whisper large-v3-turbo speech model, works in 90+ languages, and charges only for the minutes it actually transcribes. **Monitor mode** remembers what it already did and transcribes only new episodes, so you can schedule it and get every new episode as text.

### What it does

- **Direct files:** MP3, M4A, WAV, OGG/OPUS, AAC, FLAC, MP4, WEBM, MOV and most other audio/video formats, from any public http/https link.
- **Podcast RSS feeds:** transcribes the newest episodes (1-20 per feed).
- **Apple Podcasts links:** `podcasts.apple.com/.../id123456789` is resolved to the show's public RSS feed.
- **Output per file:** full text, word count, detected language, timestamped segments, optional SRT and WebVTT, episode title, publish date and feed title.
- **Monitor mode:** only new episodes or files since the last run, per Monitor ID.
- **Translated subtitles (add-on):** pick up to 5 languages in `translateTo` and get translated text plus SRT/VTT with the original timings, ready to upload to YouTube, Vimeo or a video player.
- **AI summary (add-on):** a 3-5 sentence summary, up to 6 key points and 2-8 timestamped chapters per file, for show notes and descriptions.
- **Long files:** files are split into chunks automatically; set `maxMinutesPerFile` (1-240) to transcribe only the start of long files.

Not supported: YouTube, TikTok, Instagram or other platform page links (use our [YouTube Transcript Scraper](https://apify.com/steady-scrape/youtube-transcripts) for YouTube), private or login-protected files, and speaker labels (diarization).

### How to use it

1. Add file links in **Audio or video file URLs** and/or feeds in **Podcast RSS feeds or Apple Podcasts links**.
2. Optional: set a language (or leave empty for auto-detect), choose SRT/VTT, and limit minutes per file.
3. Run. Each transcript is a dataset row; the `OUTPUT` record lists every input with its status.
4. For new episodes only, choose **Monitor** mode and schedule the Actor (daily or hourly).

#### Input example

```json
{
  "podcastFeeds": ["https://podcasts.apple.com/us/podcast/the-daily/id1200361736"],
  "maxEpisodesPerFeed": 1,
  "maxMinutesPerFile": 60,
  "subtitleFormats": ["srt"],
  "translateTo": ["es", "de"],
  "summary": true,
  "mode": "monitor",
  "monitorId": "daily-news"
}
```

#### Output example

```json
{
  "sourceType": "applePodcasts",
  "feedTitle": "The Daily",
  "episodeTitle": "Example episode",
  "publishedAt": "2026-11-16T10:45:00Z",
  "audioUrl": "https://.../episode.mp3",
  "status": "ok",
  "durationSeconds": 1712.4,
  "transcribedSeconds": 1712.4,
  "truncated": false,
  "language": "en",
  "wordCount": 4630,
  "text": "From the newsroom ...",
  "segments": [{"start": 0.0, "end": 4.2, "text": "From the newsroom ..."}],
  "srt": "1\n00:00:00,000 --> 00:00:04,200\nFrom the newsroom ...\n",
  "billedMinutes": 29,
  "translations": {"es": {"text": "Desde la redacción ...", "srt": "1\n00:00:00,000 --> 00:00:04,200\nDesde la redacción ...\n", "billedLanguageMinutes": 29}},
  "summary": {"summary": "...", "keyPoints": ["..."], "chapters": [{"start": "00:00", "title": "Intro"}], "coversFullTranscript": true}
}
```

### Pricing (pay per event)

You pay only for what runs, with no subscription:

- **Actor start:** $0.0005 per run (charged by Apify when the run starts, up to 1 GB memory).
- **audio-minute:** $0.004 per started minute of audio actually transcribed (charged once per file on the transcribed length).
- **file-processed:** $0.01 per file we download and try to transcribe, including links that turn out to be broken or not audio. Files over 80 MB are refused.
- **feed-checked:** $0.002 per RSS feed or Apple Podcasts show we read, including monitor checks with no new episodes.
- **subtitle-language-minute:** $0.0015 per started minute of transcribed audio, per translated subtitle language (add-on). Very dense transcripts count one unit per 2,000 bytes of text if that is more.
- **summary:** $0.005 per AI summary created (add-on).

Worked examples (excluding add-ons): a 1-minute clip is about $0.0145; a 60-minute episode is about $0.2505; a monitor run with no new episodes is $0.0025.

Free: invalid or blocked links that are never fetched, files skipped because of your maximum charge per run, the daily capacity limit or the free-plan limits, already-seen episodes in monitor mode, translations or summaries that fail or hit the daily capacity, and mock runs. The default maximum charge per run is $2.00; raise it in the run options for long batches.

**Free Apify plan:** up to 2 files per run, the first 10 minutes of each file and 2 subtitle languages, within a shared daily limit.

### Good to know

- Transcription runs on shared capacity with a daily limit. If it is reached, files are skipped (not charged) with a clear note; retry after 00:00 UTC.
- Accuracy depends on audio quality. Music, heavy cross-talk and very noisy audio transcribe worse.
- Only transcribe audio you have the right to use. Public podcast feeds are meant for listening; check each show's terms before republishing a transcript.
- Files over 80 MB are refused.

### Models and licences

Speech: OpenAI Whisper large-v3-turbo (MIT). Translation: Meta M2M100 1.2B (MIT). Summaries: Google Gemma 4 (Apache 2.0). All run on Cloudflare Workers AI. Machine translation and summaries can contain mistakes; review them before publishing.

### FAQ

**Does it work for video?** Yes, the audio track of MP4/WEBM/MOV files is transcribed.

**Can I get subtitles?** Choose SRT and/or WebVTT in "Subtitle files"; each row then includes the subtitle text with timestamps.

**Can I get subtitles in another language?** Yes. Add language codes in "Translated subtitles"; each language is billed per minute of audio.

**What happens if a file fails half-way?** Only the transcribed minutes are charged, and the row says the file is partial.

**How do I use it from code or an AI agent?** Call it through the Apify API or MCP server like any Actor; the input is small and every limit has a safe default.

Questions or a feature request? Open an issue on the Issues tab.

# Actor input Schema

## `audioUrls` (type: `array`):

Direct links to audio or video files (MP3, M4A, WAV, OGG, OPUS, MP4, WEBM...). Public http/https links only. YouTube, TikTok and other platform page links are not supported.

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

A podcast RSS feed URL or an Apple Podcasts show link (podcasts.apple.com/.../id123456789). The newest episodes are transcribed.

## `maxEpisodesPerFeed` (type: `integer`):

How many of the newest episodes to transcribe per feed (1-20). In monitor mode: the most new episodes per run.

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

Only the first N minutes of each file are transcribed and charged (1-240).

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

ISO code such as en, es, de, pt. Leave empty to auto-detect.

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

Adds a list of {start, end, text} segments in seconds.

## `subtitleFormats` (type: `array`):

Optional SRT and/or WebVTT text in each row.

## `translateTo` (type: `array`):

Optional. Up to 5 language codes (es, de, fr, pt, ja...). Each language gets translated text plus SRT/VTT subtitles with the original timings. Billed per language-minute.

## `summary` (type: `boolean`):

Adds a short summary, up to 6 key points and 2-8 timestamped chapters per file. Billed per summary.

## `mode` (type: `string`):

Monitor mode remembers what it already transcribed per Monitor ID. The first monitor run transcribes the newest episodes and marks the rest of the feed as seen. Schedule it daily or hourly.

## `monitorId` (type: `string`):

Name for a monitor's memory (letters, digits, . \_ -).

## `mock` (type: `boolean`):

Returns a sample transcript without downloading or transcribing anything. Nothing is charged.

## Actor input object example

```json
{
  "audioUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/3/30/LibriVox_-_Everrett_Copy_of_the_Gettysburg_Address_-_Michael_Scherer.ogg"
  ],
  "maxEpisodesPerFeed": 1,
  "maxMinutesPerFile": 60,
  "includeSegments": true,
  "translateTo": [],
  "summary": false,
  "mode": "oneOff",
  "monitorId": "default",
  "mock": false
}
```

# Actor output Schema

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

No description

## `summary` (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 = {
    "audioUrls": [
        "https://upload.wikimedia.org/wikipedia/commons/3/30/LibriVox_-_Everrett_Copy_of_the_Gettysburg_Address_-_Michael_Scherer.ogg"
    ],
    "translateTo": []
};

// Run the Actor and wait for it to finish
const run = await client.actor("steady-scrape/audio-podcast-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 = {
    "audioUrls": ["https://upload.wikimedia.org/wikipedia/commons/3/30/LibriVox_-_Everrett_Copy_of_the_Gettysburg_Address_-_Michael_Scherer.ogg"],
    "translateTo": [],
}

# Run the Actor and wait for it to finish
run = client.actor("steady-scrape/audio-podcast-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 '{
  "audioUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/3/30/LibriVox_-_Everrett_Copy_of_the_Gettysburg_Address_-_Michael_Scherer.ogg"
  ],
  "translateTo": []
}' |
apify call steady-scrape/audio-podcast-transcription --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,steady-scrape/audio-podcast-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/IJXl8ix88fgPdoX3d/builds/02xPNyYSu2izReHWl/openapi.json
