# Audio & Video to Text + SRT Subtitles: Whisper Transcriber (`spellzcode/audio-video-transcriber`) Actor

Transcribe audio and video files to text with Whisper large-v3-turbo, in 99 languages, and get SRT and VTT subtitle files with every transcript. MP3, MP4, M4A, WAV, OGG, WebM and more; files up to 10 hours. $0.008 per audio minute, subtitles included.

- **URL**: https://apify.com/spellzcode/audio-video-transcriber.md
- **Developed by:** [Mårten Fitzback](https://apify.com/spellzcode) (community)
- **Categories:** AI, Videos
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $5.60 / 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 to Text + SRT Subtitles (Whisper)

Turn audio and video files into text, with **SRT and VTT subtitle files included** in every result. This actor uses
Whisper large-v3-turbo, works in 99 languages, and handles long recordings (up to 10 hours) by splitting them into
parts and joining the timestamps back together.

**$0.008 per audio minute, subtitles included.** A one-hour podcast costs $0.48. Failed or skipped files are free.

### What you get for each file

- The full transcript as text
- The detected (or chosen) language
- An **SRT** file and a **WebVTT** file, ready for YouTube, Vimeo, Premiere, DaVinci Resolve, CapCut or an HTML5 player
- A plain **TXT** file
- Timed segments and word-level timings (optional)

### Supported files

MP3, MP4, M4A, WAV, OGG, OPUS (WhatsApp and Telegram voice notes), FLAC, AAC, WebM, MOV, MKV and most other audio or
video formats. Video files are fine: only the sound is used.

Links can be:

- direct file links (for example `https://example.com/episode-12.mp3`), including podcast RSS enclosure links;
- Google Drive, Dropbox or OneDrive share links to files shared publicly;
- files in an Apify key-value store (use the record's public URL).

Pages on YouTube, TikTok, Instagram or Spotify are not media files. They are refused straight away, and nothing is
charged.

### How to use it

1. Paste one or more audio or video links.
2. Leave the language on **Automatic**, or pick it for short or noisy files.
3. Optional: list names or terms that appear in the recording, so they are spelled right.
4. Run. Each file becomes one row in the dataset. The SRT, VTT and TXT files are in the run's key-value store, and
   each row links to them.

### Example output

```json
{
  "url": "https://example.com/interview.mp3",
  "status": "ok",
  "language": "en",
  "durationSeconds": 1834.2,
  "minutesCharged": 31,
  "wordCount": 4710,
  "text": "Welcome back to the show...",
  "srtUrl": "https://api.apify.com/v2/key-value-stores/.../records/001-interview.srt",
  "vttUrl": "https://api.apify.com/v2/key-value-stores/.../records/001-interview.vtt",
  "txtUrl": "https://api.apify.com/v2/key-value-stores/.../records/001-interview.txt",
  "segments": [{ "start": 0.0, "end": 4.2, "text": "Welcome back to the show." }]
}
```

### Pricing

Pay per event, nothing monthly:

| Event | Price |
|---|---|
| Audio minute transcribed (started minutes, subtitles included) | $0.008 |
| Actor start | $0.00005 |

Higher Apify plans get 10–30% off the per-minute price.

- 10 minutes of audio: $0.08
- 1 hour: $0.48
- 100 hours: $48 on the free tier, $33.60 on Gold and above

The free $5 monthly Apify credit covers about 10 hours of audio. Set "Maximum minutes per file" to cap any single
file, and use Apify's maximum charge per run to cap the whole run.

### Use it from n8n, Make, Zapier or code

Call the actor with the Apify API (`run-sync-get-dataset-items`) or the Apify node in n8n or Make. Common setups:

- WhatsApp or Telegram voice note to text, then to a CRM or Notion
- Podcast episode to transcript and show notes
- Video to SRT subtitles before uploading to YouTube
- Meeting recording to text, then to a summary with an LLM

### Questions

- **Accuracy?** Whisper large-v3-turbo is close to the best open speech model for most languages. Pick the language,
  and list unusual names, for the best results.
- **Speaker labels?** Not yet.
- **Privacy?** Files are downloaded into the run, converted, transcribed and deleted when the run ends. Transcripts
  stay only in your own Apify storage.
- **Something not working?** Open an issue on the actor's Issues tab with the run link. We answer quickly.

# Actor input Schema

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

Direct links to audio or video files: MP3, MP4, M4A, WAV, OGG, OPUS, FLAC, WebM, MOV and more. Google Drive, Dropbox and OneDrive share links work if the file is shared publicly. Pages on YouTube, TikTok or Instagram are not media files and are refused (free).

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

Leave on automatic detection, or pick the spoken language for best accuracy on short or noisy files.

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

Names, brands or jargon that appear in the audio, separated by commas. Helps Whisper spell them right.

## `includeTimestamps` (type: `boolean`):

Adds the timed segments and word timings to each result. SRT and VTT files are always made.

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

Files longer than this are skipped (free), so a wrong link cannot run up a bill.

## Actor input object example

```json
{
  "mediaUrls": [
    "https://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg"
  ],
  "language": "auto",
  "includeTimestamps": true,
  "maxMinutesPerFile": 240
}
```

# Actor output Schema

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

One item per file: the transcript, language, length, and links to its SRT, VTT and TXT files.

## `files` (type: `string`):

The SRT, VTT and TXT files of every transcript.

# 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://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("spellzcode/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://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg"] }

# Run the Actor and wait for it to finish
run = client.actor("spellzcode/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://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg"
  ]
}' |
apify call spellzcode/audio-video-transcriber --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,spellzcode/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/QcGwCL1glMuGZO1yT/builds/nQzpEKcdEIfY5ffYi/openapi.json