# txtts — Transcribe YouTube, X, TikTok & Podcasts (`itbe/txtts`) Actor

Real transcripts of YouTube, X and TikTok videos, podcast episodes and audio or video links, made from what is actually said, captions or not.

- **URL**: https://apify.com/itbe/txtts.md
- **Developed by:** [itbehere](https://apify.com/itbe) (community)
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $12.00 / 1,000 social video 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

## txtts — Transcribe YouTube, X, TikTok & Podcasts

**A real transcript of every video, captions or not.** Paste YouTube links, podcast episodes or feeds, or links to audio and video files, and get back clean, readable transcripts. Each result is ready to copy, search or feed into your own tools.

### What you can transcribe

- **YouTube, X (Twitter) and TikTok videos**: any public video. We transcribe what is actually said, so it works the same whether a video has captions or not.
- **Podcasts**: a single episode link, or a podcast feed (RSS). For a feed, choose how many of the newest episodes to transcribe.
- **Audio and video links**: direct links to files such as MP3, M4A, WAV or MP4.
- **Your own files**: upload them to your Apify storage and add the links under **Files**.

Up to 100 links per run. Videos and recordings can be up to 5 hours long (5 links and 30 minutes on a free Apify plan).

### What you get

One result per link, with:

- `text`: the full transcript as plain, punctuated text
- `title`, `durationSeconds` and `language`
- `srt` (optional): subtitles you can load into a video player or editor
- `segments` (optional): the transcript split into timed pieces, as JSON
- `summary` (optional): a short summary, key points and chapters with start times
- Speaker labels (optional): who is talking, as "Speaker 1", "Speaker 2"… in the text and segments
- Any of 8 languages (optional): transcripts, summaries and subtitles in English, Spanish, French, Italian, Portuguese, Hindi, Japanese or Chinese, whatever language is spoken, free
- `status`: `done`, or an `error` explaining what went wrong

Download the results as JSON, CSV, Excel or HTML, or read them through the Apify API.

### How to use it

1. Add your links under **Links**.
2. Optional: set the **Language** (two letters, such as `en` or `es`). Leave it empty and it is detected for you.
3. Optional: add **Subtitles (.srt)** or **Timestamped segments (JSON)** under **Extra formats**.
4. Optional: switch on **Summary** or **Label speakers**, or pick an **Output language**. With an output language set, switch on **Also keep the original language** to get the transcript in the spoken language too.
5. Click **Start**.

Example input:

```json
{
  "urls": [
    "https://www.youtube.com/watch?v=jNQXAC9IVRw",
    "https://feeds.npr.org/500005/podcast.xml"
  ],
  "outputFormats": ["srt"],
  "maxEpisodes": 1
}
```

Example result:

```json
{
  "url": "https://www.youtube.com/watch?v=jNQXAC9IVRw",
  "title": "Me at the zoo",
  "status": "done",
  "language": "en",
  "durationSeconds": 19,
  "text": "All right, so here we are, in front of the elephants…"
}
```

### Pricing

You pay only for transcripts that finish. Links that fail, and recordings with no usable speech, are free. Time is counted per recording and rounded up to the next full minute, so a 19-second video counts as 1 minute.

If you set a maximum cost per run, txtts stops starting new links once it's reached and never delivers a result it couldn't charge for. The lowest maximum you can set is $0.05.

**On a free Apify plan**, each run transcribes up to 5 links (a podcast feed's episodes count one each), up to 30 minutes per recording. Anything over that is skipped and not charged. Paid Apify plans have no such limit: up to 100 links per run and 5 hours per recording.

| What | Price |
|---|---|
| YouTube, X or TikTok video | $0.012 per started minute |
| Podcast episode or audio/video link | $0.008 per started minute |
| Summary, key points and chapters | $0.001 per started minute (at least $0.01) |
| Speaker labels | $0.002 per started minute, on top |
| Text to speech | $0.02 per started block of 1,000 characters |
| Starting a run | $0.00005 per run (Apify's standard start charge, per GB of memory above 1 GB) |

### Text to speech

Put text in **Text to speech** instead of links and you get back an audio file. Pick an **Output language** and your text is translated first, then read by a voice of that language. Add pauses with a spaced dash ( – ), three dots, a blank line, or an exact time like `(2s)`.

### Good to know

- Very long recordings may come back without a summary. You aren't charged for a summary you don't get.
- Private, members-only and age-restricted videos, and X posts that need a login, can't be transcribed. Instagram and Facebook links aren't supported. Live streams can be transcribed once they have ended.
- Most transcripts are ready in about a minute; long videos take a couple of minutes.
- Your audio and video files are deleted as soon as the transcript is done.

# Actor input Schema

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

YouTube, X (Twitter) and TikTok videos, podcast episode or feed links, or direct links to audio and video files.

## `files` (type: `array`):

Audio or video files to transcribe: links to files in your Apify storage (key-value store records) or any other file link. Up to 1 GB or 5 hours each.

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

Two-letter language code (en, es, de…). Leave empty to detect it automatically.

## `outputLanguage` (type: `string`):

Get transcripts, summaries and subtitles in this language, or turn text to speech into it. Free. Leave as is to keep the language that's spoken.

## `keepOriginal` (type: `boolean`):

With an output language set, also return the transcript in the language that's spoken.

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

The plain text is always included. Add subtitles (srt) and/or timestamped segments (json).

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

Add a short summary, key points and chapters to each transcript.

## `diarize` (type: `boolean`):

Mark who is talking (Speaker 1, Speaker 2…). Best for interviews, meetings and calls.

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

For podcast feed links: how many of the newest episodes to transcribe.

## `ttsText` (type: `string`):

Text to turn into speech instead of transcribing. Pauses: a spaced dash, three dots, a blank line or an exact time like (2s).

## `webJobId` (type: `string`):

Used by txtts.co itself. Leave empty.

## Actor input object example

```json
{
  "urls": [
    "https://www.youtube.com/watch?v=jNQXAC9IVRw"
  ],
  "language": "",
  "outputLanguage": "",
  "keepOriginal": false,
  "outputFormats": [],
  "summary": false,
  "diarize": false,
  "maxEpisodes": 1
}
```

# Actor output Schema

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

One item per link or file: link, title, status, language, length in seconds, the transcript text and any extras you asked for. Text to speech runs return one item with a link to the audio file.

# 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": [
        "https://www.youtube.com/watch?v=jNQXAC9IVRw"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("itbe/txtts").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": ["https://www.youtube.com/watch?v=jNQXAC9IVRw"] }

# Run the Actor and wait for it to finish
run = client.actor("itbe/txtts").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": [
    "https://www.youtube.com/watch?v=jNQXAC9IVRw"
  ]
}' |
apify call itbe/txtts --silent --output-dataset

```

## MCP server setup

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

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/tElGEtueHdEivS18h/builds/ufJGAmaSWO8oqUGdH/openapi.json