# Audio & Video Transcription | Whisper, Podcasts, SRT (`trev0n/audio-video-transcription`) Actor

Transcribe audio and video files and podcast RSS feeds to text, timestamped segments, SRT and VTT subtitles with Whisper large-v3. 99 languages, translation to English, long files.

- **URL**: https://apify.com/trev0n/audio-video-transcription.md
- **Developed by:** [Paweł](https://apify.com/trev0n) (community)
- **Categories:** AI, Videos, Developer tools
- **Features:** Limited permissions
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.00 / 1,000 audio minute (fast)s

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 & Video Transcription | Whisper, Podcasts, SRT

🎯 **Turn any audio file, video or podcast feed into an accurate transcript with timestamps and ready-made subtitles.**

Paste links to **MP3, M4A, WAV, MP4, MOV or WEBM files** or a **podcast RSS feed** and get back clean text in paragraphs, **timestamped segments**, and **SRT / WebVTT subtitle files**. Powered by **Whisper large-v3**, the most accurate open speech model, with **99 languages**, automatic language detection, optional **translation to English**, and support for **multi-hour recordings**.

### 🚀 What Does It Do?

This tool downloads each file, extracts the audio track, and transcribes it with Whisper. Long recordings are split at natural pauses so no word is cut in half, then stitched back together with exact timestamps. You get **structured, ready-to-use transcripts** in seconds per minute of audio.

💡 **Two ways to feed it:**

1. **🔗 File links**: direct links to audio or video files on your server, Dropbox, Google Cloud Storage, Amazon S3 or any CDN.
2. **📻 Podcast RSS feeds**: paste a feed URL and the newest episodes are transcribed automatically. Schedule it with **Only new episodes** and every run transcribes just what was published since the last one.

### 👥 Who Is This For?

| 🏢 Use Case                     | 💬 How It Helps                                                                  |
| ------------------------------- | -------------------------------------------------------------------------------- |
| 🎧 **Podcasters**               | Show notes, blog posts and searchable archives from every episode                |
| 🎬 **Video creators & editors** | Ready-to-upload SRT and VTT subtitles for YouTube, Vimeo or your player          |
| 🤖 **AI & RAG builders**        | Feed interviews, calls and webinars into LLMs and vector databases as clean text |
| 📈 **Market researchers**       | Monitor what competitors and industry podcasts talk about, every week            |
| 🎓 **Students & journalists**   | Transcribe lectures and interviews with timestamps you can quote from            |
| ♿ **Accessibility teams**      | Captions for every recording you publish                                         |

### ✨ Features

- 🎯 **Whisper large-v3**: state-of-the-art accuracy, choose Fast (turbo) or Accurate
- 🌍 **99 languages**: automatic detection or set the language yourself
- 🔁 **Translate to English**: transcripts of foreign-language audio in English
- 📝 **Clean paragraphs**: text broken into readable paragraphs at natural pauses
- ⏱️ **Timestamped segments**: start and end time for every sentence
- 🎞️ **SRT & WebVTT subtitles**: inline in the results and as downloadable files
- 🎥 **Video supported**: MP4, MOV, WEBM, MKV, the audio track is extracted for you
- ⏳ **Long recordings**: hours of audio, split at pauses and stitched back seamlessly
- 📻 **Podcast feeds**: newest episodes, date filter, title filter, only-new mode for schedules
- 🔤 **Vocabulary hints**: spell names, brands and jargon correctly
- 🔇 **Fair billing**: music-only or silent files, failed downloads and errors are not charged
- 💸 **Cost guards**: per-file and per-run minute limits
- 📤 **Export Anywhere**: Download results as JSON, CSV, Excel, or push to Google Sheets, Zapier, Make, or your CRM

### 🎛️ Filters & Options

| Option                                   | What It Does                                        |
| ---------------------------------------- | --------------------------------------------------- |
| 🔗 **Audio, video or podcast feed URLs** | Files or RSS feeds to transcribe                    |
| 🎯 **Model**                             | Fast (turbo) or Accurate (large-v3)                 |
| 🌍 **Language**                          | Set the spoken language or leave empty to detect it |
| 🔁 **Translate to English**              | English output for any spoken language              |
| 🔤 **Vocabulary hints**                  | Names and terms to spell correctly                  |
| 📄 **Output formats**                    | Text, timestamped segments, SRT, WebVTT             |
| 📻 **Max episodes per feed**             | How many recent episodes to transcribe              |
| 📅 **Episodes published since**          | Only episodes after a date                          |
| 🔎 **Episode title contains**            | Only matching episodes                              |
| 🆕 **Only new episodes**                 | Skip episodes transcribed in earlier runs           |
| 🗂️ **State key**                         | Separate history for separate schedules             |
| ⏱️ **Max minutes per file**              | Transcribe only the first N minutes                 |
| 💸 **Max total minutes per run**         | Budget cap for the whole run                        |
| 📦 **Max file size**                     | Skip very large downloads                           |
| ⚙️ **Files in parallel**                 | How many files are processed at once                |
| 🌐 **Proxy**                             | Only for hosts that block downloads                 |

### 📦 What You Get (Output Fields)

#### 🎧 Source

| Field        | Example                                          |
| ------------ | ------------------------------------------------ |
| url          | `https://tracking.swap.fm/track/.../default.mp3` |
| source       | `podcast`                                        |
| podcastTitle | `Planet Money`                                   |
| title        | `Are wildfires making the future uninsurable?`   |
| published    | `2026-11-13T23:49:12.000Z`                       |
| feedUrl      | `https://feeds.npr.org/510289/podcast.xml`       |

#### ⏱️ Audio

| Field          | Example                  |
| -------------- | ------------------------ |
| durationSec    | `2650`                   |
| transcribedSec | `2650`                   |
| truncated      | `false`                  |
| hasVideo       | `false`                  |
| language       | `English`                |
| model          | `whisper-large-v3-turbo` |

#### 📝 Transcript

| Field     | Example                                                                                   |
| --------- | ----------------------------------------------------------------------------------------- |
| text      | `Last November, New Mexico became the first state to launch universal free child care...` |
| wordCount | `7642`                                                                                    |
| segments  | `[{"start": 0.6, "end": 5.18, "text": "Last November, New Mexico became..."}]`            |
| srt       | `1\n00:00:00,600 --> 00:00:05,180\nLast November, New Mexico became...`                   |
| srtUrl    | `https://api.apify.com/v2/key-value-stores/.../records/62aff6b32a848375.srt`              |
| vttUrl    | `https://api.apify.com/v2/key-value-stores/.../records/62aff6b32a848375.vtt`              |

### 📊 Example Output

```json
{
    "url": "https://tracking.swap.fm/track/XvDEoI11TR00olTUO8US/.../episodes/4bb23a81/audio/128/default.mp3",
    "source": "podcast",
    "podcastTitle": "Planet Money",
    "title": "Are wildfires making the future uninsurable?",
    "published": "2026-11-13T23:49:12.000Z",
    "feedUrl": "https://feeds.npr.org/510289/podcast.xml",
    "durationSec": 2650,
    "transcribedSec": 300,
    "truncated": true,
    "hasVideo": false,
    "language": "English",
    "model": "whisper-large-v3-turbo",
    "wordCount": 873,
    "text": "Last November, New Mexico became the first state to launch universal free child care. One year later, many families are still on wait lists...",
    "segments": [
        {
            "start": 0.6,
            "end": 5.18,
            "text": "Last November, New Mexico became the first state to launch universal free child care."
        }
    ],
    "srt": "1\n00:00:00,600 --> 00:00:05,180\nLast November, New Mexico became the first state to launch universal free child care.\n",
    "srtUrl": "https://api.apify.com/v2/key-value-stores/abc123/records/62aff6b32a848375.srt",
    "scrapedAt": "2026-11-16T12:00:00.000Z"
}
```

### 📋 Dataset Views

The Apify Console gives you **3 ready-made table views** to quickly browse your results:

| View                | What It Shows                                                                |
| ------------------- | ---------------------------------------------------------------------------- |
| 📊 **Transcripts**  | Title, podcast, date, duration, language, word count, SRT link and any error |
| 📝 **Text**         | Title with the full transcript                                               |
| 📋 **Full details** | Every single field, the complete dataset                                     |

### 💰 Pricing

You pay **per started minute of audio** that was transcribed, a little more for the Accurate model. Nothing else: files that cannot be downloaded, are not media, contain no speech, or fail during transcription are **free**. Use **Max total minutes per run** or Apify's max cost per run to cap spending.

### ❓ FAQ

**🎬 Can I transcribe YouTube, TikTok or Instagram videos?**
No. This tool transcribes media you can link to directly (your own files, cloud storage, podcast CDNs). Platform pages are rejected with a clear message.

**🗣️ Does it label speakers?**
Not yet. You get timestamped sentences; speaker labels are on the roadmap.

**🌍 Which languages work?**
All 99 Whisper languages, including English, Spanish, German, French, Polish, Portuguese, Italian, Dutch, Japanese, Chinese and Arabic.

**⏳ How long can a file be?**
Hours. Long files are split at pauses and merged back with exact timestamps. Use **Max minutes per file** to transcribe only the beginning.

**📅 Can I run it on a schedule?**
Yes. Add your podcast feeds, turn on **Only new episodes**, and schedule the run daily or weekly.

### 💬 Need Something Custom?

🛠️ Need speaker labels, summaries and chapters, a Google Drive or Dropbox folder watcher, or transcripts pushed straight into Notion or your CMS? **Send me a private message on Apify** and I will build it for you. Feature requests and feedback are always welcome! 🙌

# Actor input Schema

## `startUrls` (type: `array`):

Direct links to MP3, M4A, WAV, OGG, FLAC, MP4, MOV, WEBM files (Dropbox, S3, Google Cloud, your server) or podcast RSS feeds. YouTube, TikTok and other platform pages are not supported.

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

Fast = Whisper large-v3 turbo (cheaper, great for clear speech). Accurate = Whisper large-v3 (best for accents, noise, rare languages).

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

ISO 639-1 code like en, de, pl, es. Empty = detect automatically.

## `translateToEnglish` (type: `boolean`):

Output an English translation instead of the original language (uses the Accurate model).

## `vocabulary` (type: `string`):

Names, brands and jargon that appear in the audio, e.g. "Kubernetes, Anthropic, Wrocław". Improves spelling.

## `outputFormats` (type: `array`):

What each result contains. SRT and VTT are also saved as downloadable files.

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

Newest episodes first. 0 = all episodes.

## `episodesSince` (type: `string`):

Only episodes on or after this date (YYYY-MM-DD).

## `titleIncludes` (type: `string`):

Only episodes whose title contains this text.

## `onlyNewEpisodes` (type: `boolean`):

Skip episodes already transcribed by earlier runs with the same state key. Ideal for scheduled runs.

## `stateKey` (type: `string`):

Name of the episode history used by "Only new episodes". Use different keys for separate schedules.

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

Longer files are transcribed up to this length.

## `maxTotalMinutes` (type: `integer`):

Files that would go over this budget are skipped (and not charged).

## `maxFileSizeMb` (type: `integer`):

Larger downloads are stopped.

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

How many files are processed at the same time.

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

Only needed when the file host blocks downloads.

## Actor input object example

```json
{
  "startUrls": [
    {
      "url": "https://feeds.npr.org/510289/podcast.xml"
    }
  ],
  "model": "fast",
  "translateToEnglish": false,
  "outputFormats": [
    "text",
    "segments",
    "srt"
  ],
  "maxEpisodesPerFeed": 1,
  "onlyNewEpisodes": false,
  "stateKey": "default",
  "maxMinutesPerFile": 5,
  "maxTotalMinutes": 600,
  "maxFileSizeMb": 1000,
  "maxConcurrency": 2,
  "proxyConfiguration": {
    "useApifyProxy": false
  }
}
```

# Actor output Schema

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

No description

## `files` (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 = {
    "startUrls": [
        {
            "url": "https://feeds.npr.org/510289/podcast.xml"
        }
    ],
    "maxEpisodesPerFeed": 1,
    "maxMinutesPerFile": 5
};

// Run the Actor and wait for it to finish
const run = await client.actor("trev0n/audio-video-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 = {
    "startUrls": [{ "url": "https://feeds.npr.org/510289/podcast.xml" }],
    "maxEpisodesPerFeed": 1,
    "maxMinutesPerFile": 5,
}

# Run the Actor and wait for it to finish
run = client.actor("trev0n/audio-video-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 '{
  "startUrls": [
    {
      "url": "https://feeds.npr.org/510289/podcast.xml"
    }
  ],
  "maxEpisodesPerFeed": 1,
  "maxMinutesPerFile": 5
}' |
apify call trev0n/audio-video-transcription --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,trev0n/audio-video-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/gdKbIY3AsrbcQ7axQ/builds/OBErWOe4ajsyPRZCA/openapi.json
