# Video & Podcast Transcript Extractor: TikTok, Reels, Podcasts (`datadrip/video-transcript`) Actor

Turn TikToks, Instagram Reels, Facebook videos and podcast episodes into clean, timestamped text with Whisper AI. Whole profiles and shows supported. Pay only for delivered transcripts.

- **URL**: https://apify.com/datadrip/video-transcript.md
- **Developed by:** [Ruan Bezuidenhout](https://apify.com/datadrip) (community)
- **Categories:** AI, Videos, Social media
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $10.00 / 1,000 transcripts

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

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

## Video & Podcast Transcript Extractor: TikTok, Reels, Podcasts

Turn short-form videos and podcast episodes into clean, timestamped text, ready for AI pipelines, research, content repurposing or SEO.

- **Built for TikTok, Instagram Reels, Facebook videos and podcasts.**
- **Whole podcast shows:** paste an Apple Podcasts show link or any podcast RSS feed and get the **latest N episodes** transcribed, newest first.
- **Whole profiles:** paste a profile or playlist link and set how many videos to take.
- **High-quality AI transcription:** Whisper large-v3 speech-to-text with punctuation and language detection. Native captions are used instead when a platform provides them.
- **Pay only for results:** links that fail, silent clips and videos with no detectable speech are never charged. Song lyrics count as speech.
- **No login and no cookies.** Only public content.

### Supported sources

| Source | Status |
|---|---|
| TikTok videos and profiles | ✅ Tested |
| Instagram Reels | ✅ Tested |
| Facebook videos | ✅ Tested |
| Podcast shows: Apple Podcasts show links and RSS feeds (latest N episodes) | ✅ Tested |
| Apple Podcasts episodes, direct `.mp3`/`.mp4` links | ✅ Tested |
| X/Twitter, Vimeo, SoundCloud and many other sites | Best effort |
| YouTube | ⚠️ Best effort. YouTube often refuses automated requests from cloud servers. Refused videos are returned as errors and **not charged**. |

### What you get

One row per video:

| Field | Example |
|---|---|
| `status` | `ok`, `no-speech` or `error` |
| `platform` | `TikTok`, `Instagram`, `ApplePodcasts`… |
| `title`, `uploader`, `uploadDate`, `durationSeconds` | |
| `viewCount`, `likeCount`, `commentCount` | when the platform shares them |
| `language` | detected spoken language (ISO code) |
| `source` | `captions` (native) or `ai` (Whisper) |
| `text` | the full transcript as one string |
| `segments` | `[{ "start": 0.0, "end": 2.0, "text": "Martha Dump Truck in the flesh!" }]` |
| `srt` | ready-to-use subtitle file (optional) |
| `truncated` | `true` if the audio was longer than your per-video cap |

### Input

```json
{
  "urls": [
    { "url": "https://www.tiktok.com/@creator/video/1234567890" },
    { "url": "https://www.instagram.com/reel/XXXXXXXX/" },
    { "url": "https://podcasts.apple.com/us/podcast/huberman-lab/id1545953110" },
    { "url": "https://feeds.megaphone.fm/hubermanlab" }
  ],
  "maxVideosPerSource": 20,
  "language": "",
  "maxMinutesPerVideo": 120,
  "includeSrt": false
}
```

### Pricing

| Event | Price |
|---|---|
| Transcript (includes the first 3 minutes of AI transcription) | $0.01 |
| Each extra AI minute after the first 3 | $0.005 |

Example: 100 TikToks under 3 minutes cost **$1.00**. A 60-minute podcast costs $0.01 + 57 × $0.005 = **$0.295**. Use **Max minutes per video** to cap long episodes, and runs never transcribe more than your budget allows.

### Tips

- Set **Language** (e.g. `en`, `es`) for very short clips. Auto-detection can guess wrong on a few seconds of audio.
- Platforms sometimes refuse automated requests. Those videos come back with `status: "error"` and a plain explanation, are **never charged**, and can be retried later.

### FAQ

**Is this legal?** The actor only reads publicly available content, the same as a logged-out visitor, and never tries to get around a site's bot protection. Make sure your use of the transcripts follows copyright law and each platform's terms.

**Private or age-restricted videos?** Not supported. These need a login.

# Actor input Schema

## `urls` (type: `array`):

Public links from TikTok, Instagram Reels, Facebook, podcast shows (Apple Podcasts show links or RSS feeds, latest episodes first), single episodes or direct audio/video files. Many other sites work on a best-effort basis (YouTube often refuses cloud servers; refused videos are not charged). Profiles and playlists are expanded into their videos.

## `maxVideosPerSource` (type: `integer`):

Limit for links that contain many videos. Single video links always count as one.

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

ISO code such as en, es, de. Leave empty to auto-detect the spoken language.

## `preferCaptions` (type: `boolean`):

Faster and free of AI charges. Turn off to always use AI speech-to-text (better punctuation than auto-captions).

## `maxMinutesPerVideo` (type: `integer`):

Longer audio is cut at this point and marked as truncated. Caps your cost on long podcasts.

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

Adds a list of { start, end, text } pieces, useful for clipping, search and chaptering.

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

Adds a ready-to-use .srt subtitle file as text.

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

How many videos to process at the same time.

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

Network settings for requests. The default works for most sites. Videos a platform refuses are returned as errors and never charged.

## Actor input object example

```json
{
  "urls": [
    {
      "url": "https://www.tiktok.com/@patroxofficial/video/6742501081818877190"
    }
  ],
  "maxVideosPerSource": 20,
  "preferCaptions": true,
  "maxMinutesPerVideo": 120,
  "includeSegments": true,
  "includeSrt": false,
  "maxConcurrency": 4,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

# Actor output Schema

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

All transcripts from this run, one row per video.

## `transcriptsFull` (type: `string`):

Every field, including timestamped segments and SRT.

# 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 = {
    "urls": [
        {
            "url": "https://www.tiktok.com/@patroxofficial/video/6742501081818877190"
        }
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("datadrip/video-transcript").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 = { "urls": [{ "url": "https://www.tiktok.com/@patroxofficial/video/6742501081818877190" }] }

# Run the Actor and wait for it to finish
run = client.actor("datadrip/video-transcript").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 '{
  "urls": [
    {
      "url": "https://www.tiktok.com/@patroxofficial/video/6742501081818877190"
    }
  ]
}' |
apify call datadrip/video-transcript --silent --output-dataset

```

## MCP server setup

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

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/JwQtIKIj7KROUCses/builds/Bpkr5V9QsUg4ireKs/openapi.json