# Audio Transcription: Speech to Text, MP3 & Podcast to Text, SRT (`gmyri/audio-transcriber`) Actor

Transcribe audio and video files and podcast episodes to text with Whisper: 99 languages, timestamps, SRT/VTT subtitles, translation to English. $3 per 1,000 audio minutes.

- **URL**: https://apify.com/gmyri/audio-transcriber.md
- **Developed by:** [Giorgos Myrianthous](https://apify.com/gmyri) (community)
- **Categories:** AI, Videos, Automation
- **Features:** Limited permissions
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $3.00 / 1,000 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.

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 Transcription: Speech to Text, MP3 & Podcast to Text, SRT

**Speech to text with Whisper** for audio and video files and **podcast RSS feeds**: MP3, M4A, WAV, OGG, FLAC, MP4, MOV and WEBM to **text, timestamped segments and SRT/VTT subtitles**, in 99 languages, with optional translation to English. Half the price of most Whisper transcribers on the Store.

💲 **$0.003 per audio minute ($3 per 1,000 minutes)** with the tiny/base model, $0.006 with the more accurate small model. Failed files are free. Pay only for results. No subscription, and the Apify free plan's monthly credit covers small jobs.

**Also known as:** audio transcription, speech to text, Whisper transcription, MP3 to text, podcast transcript, audio to text, video to text, SRT subtitles generator, transcribe audio API.

### Try it now (free-plan friendly)

1. Click **Start**. The prefilled input works as is. Transcribes JFK's famous 11-second quote in about 10 seconds.
2. Or paste this input into the JSON tab:

```json
{
  "audioUrls": [
    {
      "url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav"
    }
  ]
}
```

**Example output** (one dataset item, shortened):

```json
{
  "url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav",
  "status": "ok",
  "language": "en",
  "durationSec": 11.0,
  "minutesCharged": 1,
  "wordCount": 22,
  "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.",
  "srtUrl": "https://api.apify.com/v2/key-value-stores/…/records/jfk.wav-1.srt",
  "segments": [
    {
      "start": 0.0,
      "end": 7.6,
      "text": "And so my fellow Americans ask not what your country can do for you,"
    }
  ]
}
```

Small runs cost cents, and you can set a **Max cost per run** so you're never charged more.

### Use with AI agents / Apify MCP

Give your agent (Claude, ChatGPT, Cursor, n8n AI Agent, LangChain, OpenAI Agents SDK) this tool through **Apify's MCP server**:

```text
https://mcp.apify.com?tools=gmyri/audio-transcriber
```

- **Example prompt:** "Transcribe the latest episode of this podcast feed and summarise it: https://feeds.npr.org/510289/podcast.xml"
- **Why agents like it:** the input has one required field and documented defaults and enums. The output has stable, flat field names, errors are returned as items with an `error` field and are never charged, and each run writes a summary to the `OUTPUT` record.
- Agents that use `search-actors` find it by searching for: audio transcription, speech to text.

### API, Python, n8n, Make, Zapier

```bash
curl -X POST "https://api.apify.com/v2/acts/gmyri~audio-transcriber/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
  -H 'Content-Type: application/json' \
  -d '{"podcastFeeds":["https://feeds.npr.org/510289/podcast.xml"],"episodesPerFeed":1,"model":"base"}'
```

- **Python:** `ApifyClient(token).actor("gmyri/audio-transcriber").call(run_input={...})`
- **n8n / Make / Zapier:** use the Apify "Run Actor" action with `gmyri/audio-transcriber`, then read the dataset items.

### Quick FAQ

- **Does it work with YouTube or Spotify links?** No. Platform pages aren't supported. Use a direct audio/video file URL you have the right to process, or a public podcast RSS feed.
- **How fast is it?** With 4 GB memory (1 vCPU) the base model transcribes about 14 minutes of audio per minute; the default 2 GB is half that speed at the same cost per minute. Use more memory for more speed, or `tiny`.
- **Which languages?** All 99 Whisper languages, auto-detected. Set `language` to force one, or `translateToEnglish` for English output.
- **What if I set a spending limit?** The Actor stops cleanly at your *Max cost per run* and you're never charged above it.

### Details

### What it does

- **Speech to text with OpenAI Whisper** (faster-whisper, int8) running on Apify. No OpenAI key, no per-request API bill on top.
- **Any audio or video file URL:** MP3, M4A, WAV, OGG, OPUS, FLAC, AAC, MP4, MOV, WEBM. Signed S3/GCS/Dropbox links work.
- **Podcast to text:** give a podcast RSS feed and it transcribes the newest episodes from the feed's enclosures.
- **99 languages**, auto-detected, plus **translation to English**.
- **Timestamps and subtitles:** segments with start/end times, optional word-level timestamps, and **SRT / VTT / TXT files** saved for every file.
- **Voice activity detection** skips silence and reduces Whisper hallucinations.

### Typical uses

- Podcast, interview and meeting-recording transcripts for search, SEO, show notes and RAG.
- Subtitles (SRT/VTT) for your own videos.
- Feeding call recordings or voice notes you own into LLM pipelines and AI agents.
- Scheduled podcast monitoring: combine with an Apify schedule and `episodesPerFeed: 1`.

### Input

| Field | Description |
|---|---|
| `audioUrls` | Direct audio/video file URLs. |
| `podcastFeeds` | Podcast RSS feeds (newest episodes are transcribed). |
| `episodesPerFeed` | Episodes per feed (default 1). |
| `model` | `tiny`, `base` (default) or `small` (more accurate, billed at the small rate). |
| `language` | ISO code (`en`, `de`, `es`, `el`...) or empty to auto-detect. |
| `translateToEnglish` | Output an English translation. |
| `includeSegments`, `wordTimestamps`, `saveSubtitles` | Timestamp and subtitle options. |
| `maxMinutesPerFile` | Skip files longer than this (default 180). |

### Pricing

Pay per event: **$0.003 per audio minute ($3 per 1,000 minutes)** with the tiny or base model, **$0.006 per minute** with the small model, plus Apify's standard $0.00005 Actor start. Minutes are rounded up per file (an 11-second clip is 1 minute). Failed downloads, unsupported links and skipped files are free.

### Notes

- Only process audio you own or have the right to transcribe. Video/social platform pages (YouTube, TikTok, Instagram, Spotify...) are not supported: pass a direct file URL or a public podcast feed.
- Transcripts may contain whatever was said in the audio. The Actor stores results only in your own Apify storage.
- CPU Whisper is fast: a 35-minute episode takes well under a minute with `tiny` and a few minutes with `base`.

### Related tools

- [RSS Feed Reader: RSS & Atom to JSON, Find Feeds, Only New Items](https://apify.com/gmyri/rss-feed-reader)
- [PDF & Document to Markdown Parser: DOCX, PPTX, XLSX, HTML, RAG](https://apify.com/gmyri/doc-to-markdown)
- [OCR Image to Text & Scanned PDF to Text (Tesseract, 100+ langs)](https://apify.com/gmyri/image-pdf-ocr)

💡 **Need several checks per site?** [Website Audit All-in-One](https://apify.com/gmyri/website-audit) runs SEO, broken links, PageSpeed, tech stack and SSL/DNS checks in one report for $0.03 per site.

All tools by gmyri: [doc-to-markdown](https://apify.com/gmyri/doc-to-markdown), [dataset-merge-dedup](https://apify.com/gmyri/dataset-merge-dedup), [site-health-audit](https://apify.com/gmyri/site-health-audit), [website-screenshot](https://apify.com/gmyri/website-screenshot), [domain-health-check](https://apify.com/gmyri/domain-health-check), [image-pdf-ocr](https://apify.com/gmyri/image-pdf-ocr), [tech-stack-detector](https://apify.com/gmyri/tech-stack-detector), [rss-feed-reader](https://apify.com/gmyri/rss-feed-reader), [pagespeed-checker](https://apify.com/gmyri/pagespeed-checker), [website-audit](https://apify.com/gmyri/website-audit), [wayback-machine-snapshots](https://apify.com/gmyri/wayback-machine-snapshots), [image-converter](https://apify.com/gmyri/image-converter).

# Actor input Schema

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

Direct links to audio/video files: MP3, M4A, WAV, OGG, OPUS, FLAC, AAC, MP4, MOV, WEBM. Signed S3/GCS/Dropbox links work. Video platform pages (YouTube, TikTok, Spotify...) are not supported.

## `podcastFeeds` (type: `array`):

Podcast RSS feed URLs. The newest episodes (see 'Episodes per feed') are downloaded from the feed's enclosures and transcribed.

## `episodesPerFeed` (type: `integer`):

Newest episodes to transcribe from each podcast feed.

## `model` (type: `string`):

Whisper model size. 'base' is a good balance; 'small' is more accurate for accents/noisy audio and non-English, and is billed at the 'small' rate.

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

ISO code like en, de, es, fr, el, ja. Leave empty to auto-detect.

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

Output an English translation instead of the original-language transcript.

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

Add a 'segments' array (start, end, text) to each item.

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

Add per-word start/end times inside segments (slower).

## `saveSubtitles` (type: `boolean`):

Save .srt and .vtt subtitle files to the key-value store and link them in the output.

## `skipSilence` (type: `boolean`):

Voice activity detection removes long silences and reduces hallucinations.

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

Files longer than this are skipped (not charged).

## `downloadTimeoutSecs` (type: `integer`):

Per-file download timeout.

## Actor input object example

```json
{
  "audioUrls": [
    {
      "url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav"
    }
  ],
  "episodesPerFeed": 1,
  "model": "base",
  "translateToEnglish": false,
  "includeSegments": true,
  "wordTimestamps": false,
  "saveSubtitles": true,
  "skipSilence": true,
  "maxMinutesPerFile": 180,
  "downloadTimeoutSecs": 300
}
```

# Actor output Schema

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

One item per audio/video file with text, segments and subtitle links.

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

Files, minutes and failures.

# 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": [
        {
            "url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav"
        }
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("gmyri/audio-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 = { "audioUrls": [{ "url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav" }] }

# Run the Actor and wait for it to finish
run = client.actor("gmyri/audio-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 '{
  "audioUrls": [
    {
      "url": "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/samples/jfk.wav"
    }
  ]
}' |
apify call gmyri/audio-transcriber --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,gmyri/audio-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/QNIwW5xT9vqB6AubZ/builds/wIAQQdRxqxumdmsGB/openapi.json
