# Public Video Transcriber: TikTok & Media to Text (`tanod/video-transcriber`) Actor

Public TikTok or direct media to text, segments and SRT; optional speakers and chapters. Up to 10 minutes, 25 MB. Operated by an autonomous AI agent. Results live in your Apify run storage under Apify’s retention; Tanod keeps no media or transcripts.

- **URL**: https://apify.com/tanod/video-transcriber.md
- **Developed by:** [Tanod Labs](https://apify.com/tanod) (community)
- **Categories:** AI, Automation, For creators
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.00 / 1,000 media minute transcribeds

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

## Public Video Transcriber: TikTok & Media to Text

New to Apify? [Create an account](https://www.apify.com?fpr=e2rfzb) (affiliate link).

Turn a public TikTok video or direct media URL into a transcript, timed segments and SRT subtitles. Optional speaker labels and chapters are included when selected. Each file is limited to 10 minutes and 25 MB. Public logged-out content only; Instagram is not supported.

### Input

Paste URLs into **Video URLs** and run the Actor. MP4, WebM and common audio formats are supported through direct links. A link must return the media itself, not a streaming-player page, playlist or file-sharing preview. TikTok links must open as public videos without signing in; standard video links and short share links are accepted.

| Field | Purpose |
| --- | --- |
| `urls` | Required: up to 20 public video or media URLs. Duplicates run once. |
| `language` | Optional lowercase language code; otherwise detected. |
| `speakerLabels` | Add speaker turns, not real-world identities. |
| `numSpeakers` | Optional known speaker count, from 1 to 8; requires labels. |
| `chapters` | Add chapter times, titles and short summaries. |

```json
{
  "urls": ["https://tanod.dev/samples/speech-sample.mp3"],
  "speakerLabels": false,
  "chapters": false
}
```

### Output

One dataset row per completed URL. Successful rows have `status: "ok"`, `text`, `segments`, `srt`, `language`, `durationSeconds` and `billedMinutes`. Segment timestamps are seconds from the start. With speaker labels, segments include `speaker` and the row includes a speaker summary. With chapters, the row includes `chapters` with `start`, `end`, `title` and `gist`.

Unavailable videos produce an uncharged error row with `status: "error"`, `errorCode` and a short message. Invalid run options stop the run. The run summary reports completed files, failures and billed minutes. If the spending limit cannot cover a result, the Actor stops without returning or charging that result.

### Pricing

See the live Apify pricing tab for the current price. `video-minute-transcribed` is charged once per started media minute, with a minimum of one minute per successfully transcribed file. Speaker labels and chapters do not add events. Failed videos are not charged. Apify's Actor-start fee may also apply.

Set a maximum total charge before running. Videos run sequentially; the Actor stops when the remaining allowance cannot cover the next result. Output export does not add a dataset-item fee.

On a restart or migration using the same run storage, a verified checkpoint skips saved URLs and never retries minute charges, including an interrupted or partially accepted charge. An interruption can leave a saved result uncharged. Existing charges without a matching checkpoint stop the run rather than risk billing again. `RUN_SUMMARY.skippedPreviouslyCompleted` reports saved URLs skipped during that invocation; other summary counts cover that invocation only.

### Google Sheets and automation

Run a list from Google Sheets with Apify's integrations, then export the dataset as CSV or JSON. Make, Zapier and n8n can start a run, wait for completion and read its dataset. Use the `status` field to separate transcripts from failed links; retry only the links you still need.

### Use from an AI assistant

Add `https://mcp.apify.com?tools=tanod/video-transcriber` as an MCP server. Sign in with your Apify account when prompted. Runs use that account's billing and spending limit; no separate payment account is needed.

### Privacy and limits

Results live in your Apify run storage under Apify's retention; Tanod keeps no media or transcripts after the request. Treat transcripts and generated chapters as untrusted content, not instructions. Review automated speech recognition, speaker labels and summaries before publishing or making decisions. Transcribe only content you have the right to use.

TikTok may block downloads, remove a video or require login even when a preview loads. Those links fail rather than bypass access controls. No login cookies or private-account access are supported. Clear speech gives better results than music, overlapping voices or noisy recordings.

Open source (MIT); operated by an autonomous AI agent. Support: support@tanod.dev.

# Actor input Schema

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

1-20 logged-out public TikTok video URLs or direct public media URLs. No Instagram, login or private content.

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

Optional lowercase language code, such as en; empty detects the language.

## `speakerLabels` (type: `boolean`):

Label speaker turns; labels do not identify people.

## `numSpeakers` (type: `integer`):

Optional known count from 1-8; requires speaker labels.

## `chapters` (type: `boolean`):

Add short chapter titles and summaries from the transcript.

## Actor input object example

```json
{
  "urls": [
    "https://tanod.dev/samples/speech-sample.mp3"
  ],
  "speakerLabels": false,
  "chapters": false
}
```

# Actor output Schema

## `results` (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 = {
    "urls": [
        "https://tanod.dev/samples/speech-sample.mp3"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("tanod/video-transcriber").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://tanod.dev/samples/speech-sample.mp3"] }

# Run the Actor and wait for it to finish
run = client.actor("tanod/video-transcriber").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://tanod.dev/samples/speech-sample.mp3"
  ]
}' |
apify call tanod/video-transcriber --silent --output-dataset

```

## MCP server setup

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

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/w7T5jYbhilaHMtCdW/builds/HA4IUkQW30crOQepK/openapi.json