# Audio & Video Transcriber - Speech to Text With Timestamps (`appdata-labs/audio-video-transcriber`) Actor

Transcribe any public audio or video file URL — MP3, M4A, WAV, MP4, WebM and more — into timestamped passages with Whisper running inside the Actor. No API key, nothing sent to a third-party speech service. 20 languages. Pay per minute of audio transcribed.

- **URL**: https://apify.com/appdata-labs/audio-video-transcriber.md
- **Developed by:** [Kobkoon Janngam](https://apify.com/appdata-labs) (community)
- **Categories:** Agents, MCP servers, AI
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $17.50 / 1,000 audio 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.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

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 Transcriber — speech to text with timestamps

**Turn any public audio or video file into text.** Paste links to MP3, M4A, WAV or MP4 files and get the transcript back as timestamped passages. Each passage is about 30 seconds of speech with its start and end time, so you can cite it, search it or feed it to an AI agent. The transcription is done by Whisper inside the Actor: there's no API key and nothing is sent to a speech service.

**Quick start:** press **Start** with no configuration. It transcribes the first 3 minutes of two short news podcasts. Then paste your own file links.

### Sample output

| startTime | text |
|---|---|
| 0:00 | Welcome to NASA Daily, where we bring you all of NASA's previous days' proceedings in four minutes or less… |
| 0:25 | NASA's Dragonfly mission completed its most comprehensive simulated flight on Saturn's Moon Titan… |
| 0:55 | Its research archive remains publicly available. The Near Earth Object Surveyor completed testing… |
| 1:22 | Meanwhile, cyclone Arnob struck India with winds around 130 kilometers per hour… |

These rows come from the default run on 31 October 2026.

Every row also carries:

- `mediaUrl` and `fileName`
- `passage` and `passageCount`
- `startSeconds` and `endSeconds`
- `transcribedSeconds`
- `language`
- `status`
- a plain-English `note` when something needs explaining

### What you can do with it

- **Make meetings, webinars and interviews searchable.** Each passage has a timestamp, so a match takes you to the right moment.
- **Give an AI agent the audio.** It gets text in passages that fit its context, instead of a file it cannot hear.
- **Write show notes, quotes and summaries** from a recording without listening to the whole thing.
- **Build a RAG index from audio.** Each passage is a ready-made chunk.

### Input

| Field | Default | Notes |
|---|---|---|
| `mediaUrls` | 2 samples | Direct file links: MP3, M4A, AAC, WAV, OGG, OPUS, FLAC, MP4, MOV, WebM. Up to 100 per run, and each must open without signing in. |
| `language` | `en` | The spoken language. 20 are supported, including Spanish, German, Japanese, Chinese, Arabic, Hindi and Thai. |
| `maxMinutesPerFile` | `60` | Transcribe at most this many minutes from the start of each file. You pay only for minutes transcribed. |
| `passageSeconds` | `30` | The length of each passage, from 10 to 300 seconds. |

Only the minutes you ask for are read. A two-hour file with a 10-minute limit streams only its first 10 minutes. It is not downloaded in full.

### Every file gets an answer

| status | Meaning | Charged |
|---|---|---|
| `ok` | Transcribed, one row per passage | Yes, per started minute |
| `no-speech` | The audio has no recognisable speech | Yes, per started minute (the audio was processed) |
| `not-media` | The link is a web page, or the file has no audio track | No |
| `download-failed` | The link is dead or private | No |

One bad link never fails the run. The run respects your spending limit: it stops before a minute it cannot charge for.

### Good to know

- **Page links are not files.** For YouTube and similar sites, use a tool built for that site. This Actor needs the file's own URL.
- **Set the language for non-English audio.** Whisper transcribes in the language you choose. It does not detect it.
- **Accuracy** is that of Whisper base. It is very good for clear speech and podcasts, and weaker for heavy accents, crosstalk and music.

### Pricing

You pay per started minute of audio transcribed. Links that fail and web pages cost nothing.

### Works well with

Same publisher, same output conventions, same honest-failure rules:

- [**podcast-transcriber**](https://apify.com/appdata-labs/podcast-transcriber) — Type a podcast name, get its latest episodes as timestamped text.

### Disclaimer

This Actor reads only the files you link to. It scrapes no website and calls no third-party API: the speech model runs inside the Actor. Make sure you have the right to transcribe the recordings you submit.

# Actor input Schema

## `mediaUrls` (type: `array`):

Direct links to audio or video files: MP3, M4A, AAC, WAV, OGG, OPUS, FLAC, MP4, MOV, WebM. Up to 500 MB and 100 files per run. Each link must open without signing in. Page links (YouTube and similar) are not supported — use the file's own URL. A bad entry is skipped with a reason.

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

The language spoken in the audio. Whisper transcribes in this language; it does not detect it, so set it for non-English audio.

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

Transcribe at most this many minutes from the start of each file. You pay only for minutes transcribed. Up to 240. The sample run uses 3.

## `passageSeconds` (type: `integer`):

The transcript is split into passages of about this many seconds, each with its start and end time — easy to cite, and each row fits an AI agent's context. 10 to 300.

## Actor input object example

```json
{
  "mediaUrls": [
    "https://example.com/interview.mp3",
    "https://example.com/webinar.mp4"
  ],
  "language": "es",
  "maxMinutesPerFile": 120,
  "passageSeconds": 60
}
```

# Actor output Schema

## `rows` (type: `string`):

Transcribe any public audio or video file URL — MP3, M4A, WAV, MP4, WebM and more — into timestamped passages with Whisper running inside the Actor

## `summary` (type: `string`):

What was requested, what was transcribed, minutes charged and anything skipped.

# 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 = {
    "mediaUrls": [
        "https://traffic.megaphone.fm/ECM4771087285.mp3",
        "https://traffic.megaphone.fm/ECM5358659176.mp3"
    ],
    "language": "en",
    "maxMinutesPerFile": 3,
    "passageSeconds": 30
};

// Run the Actor and wait for it to finish
const run = await client.actor("appdata-labs/audio-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 = {
    "mediaUrls": [
        "https://traffic.megaphone.fm/ECM4771087285.mp3",
        "https://traffic.megaphone.fm/ECM5358659176.mp3",
    ],
    "language": "en",
    "maxMinutesPerFile": 3,
    "passageSeconds": 30,
}

# Run the Actor and wait for it to finish
run = client.actor("appdata-labs/audio-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 '{
  "mediaUrls": [
    "https://traffic.megaphone.fm/ECM4771087285.mp3",
    "https://traffic.megaphone.fm/ECM5358659176.mp3"
  ],
  "language": "en",
  "maxMinutesPerFile": 3,
  "passageSeconds": 30
}' |
apify call appdata-labs/audio-video-transcriber --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,appdata-labs/audio-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/EWDJBwqkFahk16xh0/builds/kf4XaLUkllTvvG0FX/openapi.json