# Whisper Transcriber: Audio & Video to Text, SRT & VTT (`eliai/audio-transcriber-whisper`) Actor

Speech to text with Whisper for MP3, MP4, WAV and video URLs. Text, timestamps, SRT and VTT. $0.015 per minute, failed files free.

- **URL**: https://apify.com/eliai/audio-transcriber-whisper.md
- **Developed by:** [Broke to Built](https://apify.com/eliai) (community)
- **Categories:** AI, Videos, Automation
- **Features:** Limited permissions
- **Stats:** 127 total users, 32 monthly users, 100.0% runs succeeded, 1 bookmarks
- **User rating**: No ratings yet

## Pricing

from $14.00 / 1,000 transcribed audio minutes

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

### Speech to Text: Audio & Video Transcriber (Whisper) + SRT Subtitles

**Speech to text for any public audio or video link: send an MP3, WAV, M4A, MP4 or WebM file, a podcast RSS feed, an Apple Podcasts link or a Google Drive / Dropbox share link, and get the full transcript, timestamped segments and ready .srt and .vtt subtitle files. Whisper runs inside the Actor, so you need no OpenAI key.**

| You give it | You get back | You pay (Free plan) |
|---|---|---|
| Direct URLs to mp3, wav, m4a, mp4, webm and other files FFmpeg can read, podcast RSS feeds, Apple Podcasts links, Google Drive and Dropbox share links | Transcript text, detected language, timestamped segments, SRT and WebVTT subtitles, optional word-level timestamps | **$0.015 per started minute of audio** |

Pay per result only: no subscription, no start fee. Downloads that fail and unreadable files are not charged. Paid Apify plans get Store discounts on the price above.

#### Try it in one click

The input form is already filled in with this example. Press **Start** and you get the output below.

```json
{
  "audioUrls": [
    "https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3"
  ]
}
```

The prefilled demo is the 2 min 38 s LibriVox Gettysburg Address: 3 started minutes, so one click costs $0.045 on the Free plan and ran in 83 s.

Real output from that exact input (run on 2026-09-24; long arrays shortened to a few entries and long text cut for display):

```json
[
  {
    "url": "https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3",
    "ok": true,
    "durationSeconds": 157.88,
    "transcribedSeconds": 157.88,
    "truncated": false,
    "language": "en",
    "languageProbability": 0.9997,
    "wordCount": 299,
    "text": "This is a LibriVox recording. All LibriVox recordings are in the public domain. For more information or to volunteer, pl…",
    "segments": [
      {
        "start": 0.05,
        "end": 6.01,
        "text": "This is a LibriVox recording. All LibriVox recordings are in the public domain. For more"
      },
      {
        "start": 6.01,
        "end": 13.13,
        "text": "information or to volunteer, please visit LibriVox.org."
      }
    ],
    "srt": "1\n00:00:00,050 --> 00:00:06,010\nThis is a LibriVox recording. All LibriVox recordings are in the public domain. For more…"
  }
]
```

**Give it an audio or video link, get back the transcript as plain text, timestamped segments, and ready-to-use SRT and VTT subtitle files.** Whisper runs *inside* the actor — no OpenAI key, no third-party transcription service, no separate transcription-service account is needed. Use your Apify account in the Console or an Apify token for HTTP API calls.

- **Model:** Whisper `small` (int8, CPU) via [faster-whisper](https://github.com/SYSTRAN/faster-whisper). The model is baked into the actor image, so runs start transcribing immediately — no download wait.
- **Formats:** anything FFmpeg can decode — mp3, wav, m4a, ogg, flac, opus, and the audio track of video files (mp4, webm, mov, mkv…).
- **Links it understands:** direct file URLs, podcast RSS or Atom feeds (newest episode by default), Apple Podcasts show and episode links, Google Drive and Dropbox share links.
- **Subtitles:** SRT and WebVTT in every record, plus optional per-word start/end times.
- **Languages:** Whisper's ~100 languages, auto-detected by default (detected language + probability in every record). Optional translate-to-English.

### Who uses it

- **Podcasters and video editors** who need a transcript and burn-ready SRT captions from an episode URL.
- **Journalists and researchers** turning recorded interviews into searchable text.
- **Developers** adding speech-to-text to a pipeline without holding an OpenAI or AssemblyAI key.
- **AI agents** (over Apify MCP) handed a media link that must read what was said.
- **Anyone with a media archive** who wants a bulk pass: hand it a list of URLs, get one record each.

### Input

| Field | Type | Default | What it does |
|---|---|---|---|
| `audioUrls` | string\[] | a public-domain demo mp3 | Direct audio/video file URLs, podcast RSS feeds, Apple Podcasts links, or Google Drive / Dropbox share links. One dataset record per file or episode |
| `language` | string | `""` (auto) | ISO 639-1 code (`en`, `es`, `de`, `ja`…). Empty = auto-detect |
| `format` | `both` | `text` | `segments` | `both` | `text` = plain text only; `segments` = timestamped segments + SRT + VTT only |
| `wordTimestamps` | boolean | `false` | Adds a `words` list (start, end, probability per word) to every segment. A little slower, same price |
| `translateToEnglish` | boolean | `false` | Use Whisper's translate task instead of transcribing in the original language |
| `maxFileSizeMb` | integer | `500` | Larger downloads are skipped (recorded, never charged) |
| `maxDurationMinutes` | integer | `600` | Longer audio is refused before any compute is spent. You rarely need this — the run timeout, not this cap, is what limits length, and a file that overruns the timeout returns the transcript so far |
| `maxEpisodesPerFeed` | integer | `1` | For a podcast feed or Apple Podcasts show link: how many of the newest episodes to transcribe, one record each |

### What you get

One dataset record per URL:

| Field | Meaning |
|---|---|
| `url` | The URL you supplied |
| `ok` | `true` on success, `false` on a failure (which is never charged) |
| `durationSeconds` | Decoded audio length, to 2 decimals |
| `language` | Language Whisper detected (or the one you forced) |
| `languageProbability` | Confidence in that detection, 0-1 |
| `wordCount` | Words in the transcript |
| `tookMs` | Wall-clock milliseconds for that file |
| `text` | Full transcript as one string (`format` = `both` or `text`) |
| `segments` | `[{ start, end, text }]` phrase-level, seconds (`format` = `both` or `segments`). With `wordTimestamps`, each also has `words: [{ start, end, word, probability }]` |
| `srt` | Complete SRT subtitle file as a string (`format` = `both` or `segments`) |
| `vtt` | The same subtitles as a WebVTT file, for HTML5 `<track>` and most web players (`format` = `both` or `segments`) |
| `sourceUrl`, `episodeTitle`, `publishedAt` | Present when the file came from a podcast feed or Apple Podcasts link: the link you gave, the episode's title and its publish date |
| `resolvedUrl` | Present when your link was turned into a direct file URL (Apple Podcasts, Google Drive, Dropbox) |
| `error` | Present with `ok:false` instead of the transcript when that file failed |

### Examples

**1. Transcribe one file (the built-in demo — run it with empty input)**

Input:

```json
{ "audioUrls": ["https://broke2builtai.com/samples/gettysburg_address_64kb.mp3"] }
```

Real output from that run (a 2:38 public-domain LibriVox recording), with `text`/`segments`/`srt` trimmed for space:

```json
{
  "url": "https://broke2builtai.com/samples/gettysburg_address_64kb.mp3",
  "ok": true,
  "durationSeconds": 157.88,
  "language": "en",
  "languageProbability": 0.9997,
  "wordCount": 299,
  "tookMs": 87043,
  "text": "This is a LibriVox recording. All LibriVox recordings are in the public domain. [...] Four score and seven years ago, our fathers brought forth on this continent a new nation conceived in liberty [...]",
  "segments": [
    { "start": 0.05, "end": 6.01, "text": "This is a LibriVox recording. All LibriVox recordings are in the public domain. For more" },
    { "start": 6.01, "end": 13.13, "text": "information or to volunteer, please visit LibriVox.org." }
  ],
  "srt": "1\n00:00:00,050 --> 00:00:06,010\nThis is a LibriVox recording. [...]"
}
```

That run cost **3 events = $0.045** (2:38 rounds up to 3 started minutes).

**2. Subtitles only, for a video file**

```json
{
  "audioUrls": ["https://example.com/interview.mp4"],
  "format": "segments"
}
```

You get `segments` and `srt` and no `text` field — write `srt` straight to a `.srt` file next to the video. The audio track is pulled out of the video container for you; you do not need to demux anything first.

**3. Batch, with the language forced and translation on**

```json
{
  "audioUrls": [
    "https://example.com/ep01.mp3",
    "https://example.com/ep02.mp3",
    "https://example.com/broken-link.mp3"
  ],
  "language": "es",
  "translateToEnglish": true
}
```

Three records come back. The dead link returns `{ "url": "...", "ok": false, "error": "HTTP 404 from server" }` and is **not charged**; the other two transcribe Spanish speech into English text. Forcing `language` skips detection and helps on short or noisy clips where auto-detect can guess wrong.

**4. The latest episodes of a podcast, from its feed**

```json
{
  "audioUrls": ["https://feeds.example.com/my-show.xml"],
  "maxEpisodesPerFeed": 3
}
```

Three records come back, newest episode first, each with `episodeTitle`, `publishedAt` and `sourceUrl` (the feed). An Apple Podcasts episode link (`https://podcasts.apple.com/...?i=...`) works the same way and returns that one episode. Each episode is billed by its own audio minutes; the feed itself costs nothing.

**5. Word-level timestamps for karaoke captions or clip cutting**

```json
{
  "audioUrls": ["https://example.com/interview.mp3"],
  "wordTimestamps": true
}
```

Every segment gains `words: [{ "start": 12.48, "end": 12.81, "word": "seven", "probability": 0.97 }, ...]`, with times in seconds from the start of the file.

### Call it from code

**curl** — synchronous run, JSON straight back:

```bash
curl -X POST "https://api.apify.com/v2/acts/eliai~audio-transcriber-whisper/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"audioUrls":["https://example.com/episode.mp3"]}'
```

**Python** (`pip install apify-client`):

```python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("eliai/audio-transcriber-whisper").call(
    run_input={"audioUrls": ["https://example.com/episode.mp3"]}
)
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    if row["ok"]:
        open("episode.srt", "w", encoding="utf-8").write(row["srt"])
        print(row["language"], row["wordCount"], "words")
```

**Node.js** (`npm install apify-client`):

```js
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('eliai/audio-transcriber-whisper').call({
    audioUrls: ['https://example.com/episode.mp3'],
    format: 'text',
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].text);
```

### Speed and limits (measured, not estimated)

- Whisper **small** on CPU — solid accuracy for clear speech. It is not a GPU service and will not match large-model accuracy on very noisy audio or heavy accents.
- Measured at the default 4 GB actor memory (one full CPU core): the 2:38 test file end-to-end in **87 s**, a 36-minute file in **838 s** — **roughly 2.3-2.6x faster than realtime**, varying with platform CPU contention.
- Peak memory is **flat at ~1.7 GB whatever the file length**, because audio is transcribed in 10-minute windows rather than loaded whole. A 3-minute clip and a 6-hour audiobook have the same footprint.
- About **145 minutes of audio** fit inside the default 3600 s run timeout. For longer files raise the timeout under Input > Run options, or split the file. If the timeout arrives first you still get the transcript so far, flagged `truncated`, and are charged only for the minutes actually transcribed.
- Download timeout 30 s per file; size cap **500 MB** by default (`maxFileSizeMb`, up to 1000).
- Segments are phrase-level (start/end in seconds). Set `wordTimestamps` for per-word times; it adds some processing time (not yet measured on the platform) and does not change the price.
- No speaker diarization — the transcript does not say who is talking.
- Decoding and transcription run in a **separate process**, so a crash on one file hands back the partial transcript with an explanation instead of failing your whole run.

### Pricing

Pay per event, one event: `audio-minute`.

| Event | What one event covers | Price |
|---|---|---|
| `audio-minute` | **One started minute** of audio successfully transcribed (duration rounded up) | **$0.015** |

A 2:38 file is 3 events = **$0.045**. A 45-minute podcast is 45 events = **$0.675**. There is no start fee and no monthly fee. Failed downloads, oversized or over-long files, and undecodable inputs are recorded in the dataset with `ok:false` and **never charged**.

Comparators on the Apify store, read from their listings on 2026-08-07 (check them yourself — store prices change):

| Actor | Price |
|---|---|
| **This actor** | **$0.015 / audio-minute** |
| memo23/video-audio-transcriber | $0.0008 / second of media = $0.048 / audio-minute, plus a start fee (read 2026-10-22) |

Honest note: this is cheaper than GPU-backed services partly because you are not paying for idle GPU time, and partly because it is slower per minute of audio. That trade is the product.

### When NOT to use this

- **You need a YouTube, TikTok, or Spotify link transcribed.** This takes a media file URL, a podcast feed, or an Apple Podcasts, Google Drive or Dropbox link. A watch page is not a file. Send one anyway and you get a plain-English row telling you so, free of charge. For YouTube use [`eliai/youtube-transcript-clean`](https://apify.com/eliai/youtube-transcript-clean); for TikTok use [`eliai/tiktok-transcript-clean`](https://apify.com/eliai/tiktok-transcript-clean).
- **You need to know who said what.** There is no speaker diarization.
- **You need a 3-hour file back in five minutes.** CPU Whisper runs slower than realtime; a long file is a long run. Split it, raise memory, or use a GPU service.
- **The audio is heavily accented, very noisy, or highly technical and you cannot tolerate errors.** `small` is a good general model, not a medical or legal transcription service. Always review before publishing.
- **The file is private or behind a login.** Only public URLs you supply are fetched — no credentials, no cookies.

### FAQ

**How do I transcribe a podcast episode to text?** Paste the show's RSS feed URL, its Apple Podcasts link, or the episode's direct `.mp3` URL into `audioUrls` and run it. A feed or show link transcribes the newest episode (raise `maxEpisodesPerFeed` for more); an Apple Podcasts episode link transcribes that episode. You get the plain text, the timestamped segments, and SRT and VTT subtitles.

**Can I get WebVTT (.vtt) subtitles or word-level timestamps?** Yes. Every record has both `srt` and `vtt`. Set `wordTimestamps` to `true` for each word's own start and end time inside the segments.

**Does it work with Google Drive or Dropbox links?** Yes, if the file is shared as "anyone with the link". Paste the normal share link; the Actor turns it into a direct download. A private file returns a plain-English error and is not charged.

**How do I generate SRT subtitles from a video?** Pass the video URL (mp4, webm, mov, mkv) and set `format` to `segments`. The `srt` field in the result is a complete subtitle file — write it to a `.srt` next to your video. The audio track is extracted for you.

**Do I need an OpenAI API key?** No. Whisper runs inside this actor; there is no external API call and no key to manage. That is the main reason to use it over a wrapper around someone else's API.

**Which Whisper model does it use, and can I change it?** Whisper `small`, int8-quantized, on CPU. The model is fixed — it is baked into the image so runs start instantly. If you need `large-v3` accuracy, this is not the right actor.

**Can it transcribe a language other than English?** Yes, around 100 languages, auto-detected. Set `language` to an ISO 639-1 code to skip detection (more reliable on short or noisy clips), and set `translateToEnglish` to get English output from non-English speech.

**How much does it cost to transcribe an hour of audio?** 60 started minutes = 60 events = **$0.90** on the Free plan, less on paid Apify plans. Failures cost nothing.

**How do I convert a video to text?** Put the video's direct file URL (mp4, webm, mov, mkv) in `audioUrls`. The Actor pulls out the audio track and returns the spoken words as `text`, plus `segments` and `srt` if you want captions. It needs a link to the file itself. A YouTube or TikTok page URL is not a media file: the record says so, names the Actor that reads that site's captions, and is not charged.

**How long does a run take?** Roughly 0.4-0.45 minutes of processing per minute of audio at the default 4 GB memory — about 2.3-2.6x faster than realtime (measured: 87s end-to-end for a 2:38 clip, 838s for a 36-minute file). About 145 minutes of audio fit inside the default 3600s run timeout; for anything longer, raise the timeout under Input > Run options, or split the file.

**What happens if the transcriber crashes half way through my file?** You get the part it finished, marked `ok:false` with the reason, and **you are not charged for that file at all**. Decoding and transcription run in a separate process precisely so that a crash returns a partial transcript instead of a failed run.

### Changelog

- 2026-10-22: WebVTT subtitles in every record next to SRT. Optional word-level timestamps (`wordTimestamps`). Podcast RSS feeds, Apple Podcasts links and Google Drive / Dropbox share links are now transcribed instead of refused; feeds give the newest episode by default (`maxEpisodesPerFeed`). Same price.

- 2026-10-05: Price per transcribed minute halved to $0.015 on the Free plan (lower on paid Apify plans). Same model and output.

- 2026-09-24: New summary at the top of this page: what you send, what you get, the price, and a real output from the prefilled example.
  **2026-09-05 (listing clarity).** Clarified Apify authentication and added audio, video and subtitle terms to the search preview so users can identify supported inputs and outputs. No runtime or pricing change.

**2026-08-27 (0.2.19).** Download wait is 90s (was 30). Instagram/Facebook/Vimeo/X page URLs get a plain-language refusal instead of an FFmpeg errno. A leftover throw after the Actor context closes exits 0 so it cannot paint the listing red. No price change.

**2026-08-27.** Listing bake: the FAQ and Pricing sections that were already in source are now in the README the store actually serves (they lived in git, not in the live build). No code or price change.

**2026-08-27 (health).** Parent process now asks the Linux OOM killer to spare it (PID 1) and the transcriber child volunteers to die instead, with its address space capped short of the container. A memory death that used to fail the whole run should now return the transcript so far, uncharged. No price change.

**2026-08-22.** Decoding and transcription moved into a child process. Some media files could previously kill the run outright — an out-of-memory kill or a decoder crash inside FFmpeg stops a process without raising an error anyone can catch, so the run ended as a bare failure with no output and no explanation. Those deaths are now contained: you get every minute that was transcribed before it stopped, a plain-English reason, and no charge for that file. Also: URLs that return a web page instead of a media file (YouTube, Spotify, or any HTML page) now say so and name the Actor that does the job, instead of returning an FFmpeg error code.

**What happens if one URL in my batch is dead?** That record comes back with `ok:false` and an `error` message, the rest still transcribe, and the failure is never charged.

### Who made this

Broke to Built — a company of machines, building things
it gives away. This is one of them; the rest are free too.

### For AI agents

This Actor is built to be called by software, not just by people.

- **Mount it directly as an MCP tool** — no Store search, no ranking, just this one tool:
  `https://mcp.apify.com/?actors=eliai/audio-transcriber-whisper`
- **Or call it over HTTP** and get the results in the same request:
  `POST https://api.apify.com/v2/acts/eliai~audio-transcriber-whisper/run-sync-get-dataset-items`
- **Pay with x402, without an Apify account.** This Actor is whitelisted for agentic payments, so an agent holding USDC on Base can buy a prepaid token and spend it here. The minimum purchase is $1, the token balance is an absolute spending cap, and it expires 14 days after purchase.
- **Costs are predictable before you call.** Pricing is pay-per-event (see Pricing above), so an agent can budget a run in advance instead of discovering the bill afterwards.
- **Send only the field you mean.** If you pass the bulk field, it is used on its own; the single-value field is a fallback, never merged into your request. You are charged for the items you sent and nothing else.

# Actor input Schema

## `audioUrls` (type: `array`):

Links to transcribe, one per line. Accepts direct audio or video files (mp3, wav, m4a, ogg, flac, mp4, webm, mov, …), podcast RSS feeds (the newest episode by default, see maxEpisodesPerFeed), Apple Podcasts show or episode links, and Google Drive or Dropbox share links (shared as 'anyone with the link'). Each file becomes one dataset record with text, segments, SRT and VTT. YouTube and TikTok pages are not media files: use the YouTube or TikTok transcript Actors instead.

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

ISO 639-1 code of the spoken language, e.g. `en`, `es`, `de`, `fr`, `ja`. Leave empty to auto-detect (the detected language and its probability are included in every record).

## `format` (type: `string`):

`both` returns plain text AND timestamped segments + SRT. `text` returns only the plain text. `segments` returns only the timestamped segments + SRT.

## `wordTimestamps` (type: `boolean`):

Add a `words` list to every segment: each word with its own start, end and probability, for karaoke captions, clip cutting or search-to-the-second. Needs `format` set to `both` or `segments`. Takes a little longer; the price per audio-minute is the same.

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

Translate the speech into English instead of transcribing in the original language (Whisper's built-in translate task).

## `accuracy` (type: `string`):

`fast` (default) decodes greedily and is the right choice for clear speech: podcasts, meetings, interviews, lectures. `accurate` runs beam search with 5 beams, which can help on noisy audio, heavy accents or unusual vocabulary, and takes a little longer. The price per audio-minute is the same either way.

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

Downloads larger than this are skipped (recorded as failed, never charged).

## `maxDurationMinutes` (type: `integer`):

Audio longer than this is refused up front, before any compute is spent, and never charged. You rarely need to change it: length no longer costs memory (audio is transcribed in 10-minute windows), so the practical limit is the run TIMEOUT, not the file. About 145 minutes fit inside the default 3600s timeout; if the timeout arrives first you still get the transcript so far, flagged `truncated`, charged only for the minutes actually transcribed. Lower this if you would rather a long file be refused outright than partially transcribed.

## `maxEpisodesPerFeed` (type: `integer`):

When a link is a podcast RSS feed or an Apple Podcasts show page, transcribe this many of its newest episodes, one record each (each billed by its own audio minutes). Default 1, the latest episode.

## Actor input object example

```json
{
  "audioUrls": [
    "https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3"
  ],
  "language": "",
  "format": "both",
  "wordTimestamps": false,
  "translateToEnglish": false,
  "accuracy": "fast",
  "maxFileSizeMb": 500,
  "maxDurationMinutes": 600,
  "maxEpisodesPerFeed": 1
}
```

# Actor output Schema

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

Every item this run produced. Export as JSON, CSV or Excel from the dataset view.

# 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 = {
    "audioUrls": [
        "https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("eliai/audio-transcriber-whisper").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 = { "audioUrls": ["https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3"] }

# Run the Actor and wait for it to finish
run = client.actor("eliai/audio-transcriber-whisper").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 '{
  "audioUrls": [
    "https://archive.org/download/gettysburg_johng_librivox/gettysburg_address_64kb.mp3"
  ]
}' |
apify call eliai/audio-transcriber-whisper --silent --output-dataset

```

## MCP server setup

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

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/eb505646SmdvrObVP/builds/oZfbdvfM2BBTMc3Pi/openapi.json