Audio and Video Transcriber: Whisper text, timestamps, SRT

🎙️ What is Audio and Video Transcriber?

OpenAI Whisper running on our servers will transcribe audio and video you point it at: WAV, M4A, AAC, FLAC, OGG, Opus, MOV, WebM, MKV or anything else ffmpeg reads. Each result holds word count, duration and optional WebVTT and SubRip files, with translation to English and three model sizes. No key of your own is needed.

• Podcasts and interviews: searchable text and show notes from every episode
• Meetings and calls: minutes from recordings
• Subtitles: SRT and WebVTT files for video editors and players
• Archives: make old recordings searchable

✨ Why use this Actor?

• ✅ Subtitles included: SRT and WebVTT next to the text and timed segments
• ✅ Pick the model: tiny for speed, base as default, small for noisy or old recordings
• ✅ Translate: any of 28 languages to English text
• ✅ Files you own: URLs or uploads to the run's key-value store, up to 200 per run
• ✅ Fair billing: per started audio minute; files that fail are not charged

📦 What data can you get with Audio and Video Transcriber?

⏱️ Duration in seconds	🔢 Word count	📄 Full text
🧩 Timed segments	💬 SRT subtitles	🌐 WebVTT subtitles

SRT, WebVTT and segments are optional switches. Files that fail return an error row.

🚀 How to use Audio and Video Transcriber

Audio and Video Transcriber works in a few clicks, no coding needed:

1. Create a free Apify account (the free plan includes 5 USD of monthly credit).
2. Open Audio and Video Transcriber and click Try for free.
3. Paste the file URLs (or upload files), choose model and language, and switch on the subtitle formats you need.
4. Click Start and wait for the run to finish (most runs take seconds).
5. Download your data as JSON, CSV, Excel, XML or HTML, or send it straight to Google Sheets, Make, Zapier or your AI agent.

⬇️ Input

Enter file URLs or the keys of uploaded files; everything else has defaults (base model, English, transcribe, segments on).

Model

tiny (quickest), base (balanced, default) or small (most accurate on noisy or old recordings).

Task

transcribe keeps the spoken language; translate returns English.

Not supported

YouTube, TikTok and Instagram links are refused because their terms do not allow downloading. Use files you own or may use.

Field	Type	What it does	Default
Audio or video URLs (mediaUrls)	array	Direct links to audio or video files (MP3, WAV, M4A, AAC, FLAC, OGG, Opus, MP4, MOV, WebM, MKV and more).	["https://raw.githubusercontent.com/open
Uploaded files (storeKeys)	array	Keys of files stored in this run's default key-value store (upload them with the API before the run starts).
Whisper model (model)	string	Larger models are more accurate on accents, noise and names, and take longer.	"base"
Spoken language (language)	string	The language spoken in the files.	"en"
Task (task)	string	Translate gives English text with timestamps from speech in any supported language.	"transcribe"
Timed segments (includeSegments)	boolean	Every segment with start and end in seconds.	true
SRT subtitles (includeSrt)	boolean	Add an SRT subtitle file as text to each row.	false
WebVTT subtitles (includeVtt)	boolean	Add a WebVTT subtitle file as text to each row.	false
Max minutes per file (maxDurationMin)	integer	Longer files are transcribed up to this point and marked truncated; you pay only for the minutes transcribed.	120
Max file size (maxSizeMb)	integer	Larger files are skipped with an error line and not charged.	200
Download retries (maxRetries)	integer	Retries on network errors, rate limits and server errors.	3

Input example

{
    "mediaUrls": [
        "https://raw.githubusercontent.com/openai/whisper/main/tests/jfk.flac"
    ],
    "language": "en"
}

⬆️ Output

Every file becomes one row with the text, duration, word count and, if switched on, segments and subtitles.

Output example

One row of the dataset (the JFK inaugural address clip, a real local run of 2026-10-15):

{
    "durationSeconds": 11,
    "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.",
    "segments": [
        {
            "start": 0,
            "end": 11,
            "text": "And so my fellow Americans ask not what your country can do for you, ask what you can do for your country."
        }
    ]
}

View the results as a table or JSON in the Output tab and download them as JSON, CSV, Excel, XML, HTML or RSS, all fields or only those you pick.

💰 How much does Audio and Video Transcriber cost?

Audio and Video Transcriber is priced per event: 6 USD per 1,000 audio minutes (0.006 USD each), with no monthly rental. Inputs that fail (download, format, no audio) are free; truncated ones are charged only for what was transcribed.

You get	You pay
100 audio minutes	0.6 USD
1,000 audio minutes	6 USD
10,000 audio minutes	60 USD
100,000 audio minutes	600 USD

💡 Apify's free plan gives you 5 USD of credit every month, enough for about 833 audio minutes at no cost. Set a spending limit per run and the Actor stops there.

⚖️ Audio and Video Transcriber vs. the alternatives

	Audio and Video Transcriber	Whisper API	Manual transcription
No API key needed	✅	❌	✅
SRT and WebVTT	✅	✅	❌
Many files in one run	✅	script needed	❌
Export, schedule, API and MCP	✅	❌	❌

🔌 Integrations, API and MCP

Connect Audio and Video Transcriber to your AI agent (MCP)

Give Claude, ChatGPT, Cursor or any MCP client direct access to Audio and Video Transcriber through the Apify MCP server. Add this URL to its settings:

https://mcp.apify.com/?actors=bepolabs/media-transcriber

For Claude Desktop, add it under mcpServers in claude_desktop_config.json:

{
    "mcpServers": {
        "media-transcriber": {
            "command": "npx",
            "args": [
                "-y",
                "@apify/actors-mcp-server",
                "--actors",
                "bepolabs/media-transcriber"
            ],
            "env": {
                "APIFY_TOKEN": "<your Apify API token>"
            }
        }
    }
}

Then just ask: "Transcribe this podcast episode URL with the small model and give me the SRT subtitles."

Run it from your code

Python (pip install apify-client):

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("bepolabs/media-transcriber").call(run_input={"mediaUrls":["https://raw.githubusercontent.com/openai/whisper/main/tests/jfk.flac"],"language":"en"})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

JavaScript (npm install apify-client):

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('bepolabs/media-transcriber').call({"mediaUrls":["https://raw.githubusercontent.com/openai/whisper/main/tests/jfk.flac"],"language":"en"});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

No-code integrations

Send results to Google Sheets, Slack, Airtable, HubSpot, Make, Zapier, n8n and more from the Integrations tab, start runs on a schedule, or trigger your own endpoint with a webhook when a run finishes. The Apify API gives you full control over runs and datasets.

❓ FAQ

Can I transcribe YouTube links?

No, downloads from TikTok, Instagram and YouTube are refused; for captions from the last one, our separate transcripts Actor does the job.

How accurate is it?

Whisper is strong on clear speech. Noisy or old recordings read better with the small model. Speaker names are not included.

What does it cost?

0.006 USD per started audio minute. Failed files are free.

Is it legal to use Audio and Video Transcriber?

Transcribe only files you own or have the right to use. Whisper weights are MIT licensed (OpenAI), transformers.js is Apache-2.0, and ffmpeg runs as a separate program.

What if something is missing or does not work?

Open an issue on the Issues tab; we read each one and reply. Feature requests are welcome too.

💬 Your feedback

Tell us what Audio and Video Transcriber should add on the Issues tab or leave a review; your notes decide what we work on next.

🔗 Related Actors

Actor	What it does
📝 YouTube Transcripts	Full text and timed segments of the captions of any YouTube video, ready for summaries, search and LLMs.
🔤 Image OCR	Extract text from images in 29 languages: plain text, clean Markdown and every word with its pixel box and confidence.
📄 PDF to Text and Markdown	PDFs to clean text and Markdown, per page, per document or as RAG chunks, with columns in reading order and headers and footers removed.
🎙️ Podcast Episodes	Search terms, Apple Podcasts ids or RSS feeds to every show and its episodes, with audio links, dates and durations.
📰 RSS Feed Reader	Any RSS, Atom or JSON feed, or just a website URL, to one clean list of articles, with full text on request.
🕰️ Wayback Machine Scraper	The archive history of any URL or domain: first and last seen, every capture, and the page text of old versions.
📝 Website to Markdown	Any web page or docs site to clean Markdown for LLMs, RAG and AI agents, with headings, links and ready-made chunks.
📸 Website Screenshot	Full-page PNG, JPEG or PDF of any URL, on desktop, tablet and phone, with cookie banners closed.