# Whisper Transcriber — Audio & Video to Text, 90+ Languages (`lergassy/whisper-transcriber`) Actor

Whisper large v3 transcription with no API key to set up: MP3, WAV, M4A, FLAC, OGG, MP4, MOV and WEBM in, clean text with timecodes out, in 90+ languages. Files of any length, optional speaker labels, translation to English and SRT or WebVTT subtitles.

- **URL**: https://apify.com/lergassy/whisper-transcriber.md
- **Developed by:** [Matvey](https://apify.com/lergassy) (community)
- **Categories:** AI, Developer tools, Videos
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $21.00 / 1,000 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?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

**Whisper Transcriber** runs **Whisper large v3** on your audio and video and gives back clean text with timecodes — in 90+ languages, with no API key to set up and no model to choose. MP3, M4A, WAV, FLAC, OGG, MP4, MOV, WEBM: anything with sound. Files of any length are split, transcribed and stitched back together, so a three-hour recording is one input and one row of output.

### What it does

| What you give it | What you get back |
| --- | --- |
| An MP3 or WAV link | Transcript with timed passages |
| A video file | The same — the video track is discarded |
| A three-hour podcast | One transcript, timings continuous across parts |
| A recording in any language | Text in that language, or translated to English |
| `diarize: true` | Every passage labelled with who is speaking |
| `subtitleFormat: srt` | A finished SRT or WebVTT file |
| `chunkForRag: true` | Chunks with timecodes, ready to embed |

Two recognition settings: **accurate** (Whisper large v3, the default here) and **fast** (the distilled model, English only, several times quicker). A vocabulary hint helps with names and jargon the model has not met.

### What data does it return?

| Field | Example |
| --- | --- |
| `source`, `fileName` | `https://example.com/episode-12.mp3` · `episode-12.mp3` |
| `durationSeconds`, `durationMinutes` | `461.05` · `7.68` |
| `language`, `model`, `translatedToEnglish` | `English` · `accurate` · `false` |
| `transcript`, `wordCount`, `charCount` | the full text · `1665` · `9218` |
| `segments` | `[{"start": 0, "duration": 4.56, "text": "…", "speaker": "Speaker 1"}]` |
| `speakerCount`, `speakers` | `3` · `["Speaker 1", "Speaker 2", "Speaker 3"]` |
| `chunks` | `[{"index": 0, "startTimecode": "00:00:00", "text": "…"}]` |
| `subtitles` | a complete SRT or WebVTT file |
| `status`, `errorCode`, `errorMessage` | `ok`, or why a file failed |

### How much does it cost?

| Event | Price | When it is charged |
| --- | --- | --- |
| Minute transcribed | $0.03 | Per started minute, using the built-in key |
| Minute with your own key | $0.012 | Per started minute when you supply a Groq key |
| Add-on: Speaker labels | $0.012 | Per started minute, only when speaker labels are on |
| File processed | $0.002 | Per file downloaded and prepared |

A failed file is returned as an error row and is never charged. Larger monthly plans get 10–30 % off.

### Notes

The recognition key is built in — there is nothing to sign up for. If you already pay for a Groq key, paste it and the per-minute price drops by 60 %.

Files come from public URLs or from an upload. Very large files are limited by `maxFileSizeMb` (500 MB by default) and each file by `timeoutPerFileSecs`.

# Actor input Schema

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

Direct links to media files: MP3, M4A, WAV, FLAC, OGG, MP4, MOV, WEBM and anything else ffmpeg can read. Video files are stripped to their audio track automatically.

## `file` (type: `string`):

Upload one audio or video file from your computer instead of giving a URL.

## `quality` (type: `string`):

Fast is the everyday choice. Accurate makes fewer mistakes on accents, noise and technical vocabulary, and costs more.

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

Two-letter code of the language spoken, for example <code>en</code>, <code>ru</code>, <code>id</code>. Leave empty to detect it automatically.

## `translateToEnglish` (type: `boolean`):

Return an English transcript no matter what language is spoken.

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

Mark who is speaking in each part of the recording. Every segment gets a speaker ("Speaker 1", "Speaker 2", …), the transcript is laid out as a conversation, and subtitles carry the names. Charged per minute on top of the transcription, and slow: the speaker model runs on the machine, so expect several minutes of processing per hour of audio, while a plain transcript is near-instant.

## `speakerCount` (type: `integer`):

How many people talk in the recording. Leave empty and the Actor works it out on its own; set it when you already know, for example two people in an interview.

## `vocabularyHint` (type: `string`):

Names, jargon or spellings that appear in the audio, comma separated. Helps the engine get proper nouns right.

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

Return every recognised passage with its start time and duration, alongside the full transcript.

## `chunkForRag` (type: `boolean`):

Split the transcript into retrieval chunks that keep the timecode where each one starts.

## `chunkSize` (type: `integer`):

Target size of one chunk. Chunks break on sentence ends, so real sizes vary.

## `chunkOverlapSeconds` (type: `integer`):

How many seconds of the previous chunk to repeat at the start of the next one.

## `subtitleFormat` (type: `string`):

Also return a ready-made subtitle file as text.

## `apiKey` (type: `string`):

Optional. Supply your own key and the per-minute price drops sharply; you then pay Groq directly for the recognition. Leave empty to use the built-in key with nothing to set up.

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

How many files to transcribe at the same time.

## `maxFileSizeMb` (type: `integer`):

Files larger than this are skipped with an error row instead of being downloaded.

## `timeoutPerFileSecs` (type: `integer`):

How long one file may take to download and recognise before it is given up on.

## Actor input object example

```json
{
  "urls": [
    "https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-5min.m4a"
  ],
  "quality": "accurate",
  "translateToEnglish": false,
  "diarize": false,
  "includeSegments": true,
  "chunkForRag": false,
  "chunkSize": 1200,
  "chunkOverlapSeconds": 0,
  "subtitleFormat": "none",
  "maxConcurrency": 3,
  "maxFileSizeMb": 500,
  "timeoutPerFileSecs": 600
}
```

# Actor output Schema

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

Dataset with one row per audio or video file.

## `transcriptsInConsole` (type: `string`):

Browse the transcripts in the Apify Console.

# 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://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-5min.m4a"
    ],
    "quality": "accurate"
};

// Run the Actor and wait for it to finish
const run = await client.actor("lergassy/whisper-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://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-5min.m4a"],
    "quality": "accurate",
}

# Run the Actor and wait for it to finish
run = client.actor("lergassy/whisper-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://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-5min.m4a"
  ],
  "quality": "accurate"
}' |
apify call lergassy/whisper-transcriber --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,lergassy/whisper-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/g66vjjmwdBMoybNNb/builds/v0xsVFZBwpQMNFgm3/openapi.json