Podcast Transcriber: Audio to Text (Whisper)

sourceUrl	https://www.archive.org/download/aesop_fables_volume_three_librivox/fa…
sourceType	url
durationSec	77.95

How to use it: 3 steps

Make a free Apify accountApify is the cloud platform where our tools run. The free plan gives you $5 of usage every month, no credit card needed. You pay Apify, not us.
Paste your input and press StartNo code needed: you fill in a form (the input). It already has a working example. For example: ["https://www.archive.org/download/aesop_fables_volume_three… in Audio or video file URLs. Each start is one run.
Download the resultsWhen the run ends, the results are in a table (the dataset). Open Output, press Export and pick Excel or CSV. JSON and the API are there too.

This tool is an Apify Actor: a small program that runs on Apify. You can also run it on a schedule, for example every Monday. New to it? Read how it works, step by step and the 8 words you need first.

Made by Cliqto Media, an independent digital media company. We made this tool and keep it working. About us

What it does

Podcast and audio transcription with timestamps. Add direct links to MP3, M4A, WAV, OGG, Opus or MP4 files, or a podcast RSS feed, and get the text, plus SRT or VTT subtitles if you want them.

Input: direct media links (audioUrls), or a podcast RSS feed or Apple Podcasts show link (podcastRssUrl).
Output: the transcript text, timed segments {start, end, text}, SRT or WebVTT subtitles, the detected language and the episode details from the feed.
Languages: Whisper detects the spoken language. You can also choose it, or translate the speech to English.
Privacy: the audio is processed inside the run and is not saved to storage.

Good for

Transcribe the newest episodes of a podcast from its RSS feed.
Make SRT or VTT subtitles for a video file you host.
Turn interviews, lectures and voice notes into searchable text for notes, search or an AI pipeline.

Not a good fit

No downloads from YouTube, TikTok, Spotify, Instagram or other page links. The link must point straight to a media file (the URL usually ends with .mp3, .m4a, .wav, .ogg, .mp4 and so on).
No speaker labels (who said what). There is one text stream per file.
Live streams are not supported.
Whisper can misspell names and rare words. Check important quotes against the audio.

Who uses it

Podcasters

Get text for show notes and search from new episodes.

Video makers

Make SRT or VTT subtitles for videos you host.

Researchers and students

Turn interviews and lectures into searchable text.

Price

Pay per event: you pay for each result the tool saves, plus a small start fee for each run. The price includes Apify platform costs. Apify bills you, not us. Prices below are for the Apify free plan.

What you pay for	Price	When
Start fee	$0.01	Charged once per run, one fee per GB of memory. This tool uses 2 GB by default, so $0.02 per run.
Transcribed minute (tiny/base)	$0.0098 (from $0.0083 on paid Apify plans)	One started minute of audio transcribed with the tiny or base model, counted per file. Broken links, missing files, web pages and skipped files are not charged.
Transcribed minute (small model)	$0.032 (from $0.028 on paid Apify plans)	One started minute of audio transcribed with the more accurate small model, counted per file. Broken links, missing files, web pages and skipped files are not charged.

Examples

One minute of audio: about $0.03.
1,000 minutes of audio: about $9.82.
Every day 100 minutes of audio, for 30 days: about $30.00 a month.

Free to try: the Apify free plan gives you $5 of usage every month, no credit card needed. That is enough for about 500 minutes of audio.

Prices checked on 24 October 2026. See the current price on Apify.

Questions

Can I paste a YouTube or Spotify link?

No. The link must point straight to a media file, like an .mp3 or .mp4. For page links, use our Video URL to Text tool.

Does it know who is speaking?

No. There are no speaker labels.

Are my files stored?

No. The file is transcribed and deleted. Only the text is saved.

How long can a file be?

Up to 180 minutes and 1.5 GB per file.

Do I need an OpenAI or other API key?

No. The Whisper model runs inside the Actor. You only pay the Apify events above.

Which languages work?

Whisper supports about 100 languages. We tested English and Spanish. Quality is best for English and other widely spoken languages; small helps for others.

Details

Step by step on Apify

Open the Input tab.
In Audio or video URLs (audioUrls), keep the example LibriVox file or paste your own direct media link.
Keep the defaults: model base and output segments.
Click Start.
Open the Transcripts view in the Output tab and read the text column.

Use cases

Task	Input	You get	Key fields	Next step
Podcast show notes and search	`podcastRssUrl` + `maxEpisodes`	one row per episode	`title`, `publishedAt`, `text`, `segments`	send `text` to a summary or search tool
Subtitles for your video	`audioUrls` + `outputFormat: srt`	one row per file	`subtitles`, `language`	save `subtitles` as a `.srt` file
Meeting or interview notes	`audioUrls`	one row per file	`text`, `wordCount`, `durationSec`	paste `text` into notes or an AI agent
English version of foreign audio	`audioUrls` + `translateToEnglish`	one row per file	`text`, `language`, `task`	read or index the English text

Tips for better results

Use the podcast RSS feed to get the newest episodes in one go.
Put many files in one run to share the start fee.
Turn on translate to get English text from other languages.

Limits and good to know

Up to 180 minutes per file (maxDurationMinutes), up to 100 links and 50 feed episodes per run
Files up to 1.5 GB
The default run timeout is 3600 seconds. A 3-hour file with base at 2048 MB takes about 38 minutes. For several long files, raise the timeout or the memory
When the run timeout comes near, the current file is saved as partial and the remaining files get RUN_TIME_LIMIT
Partial and failed rows are never charged for audio that was not transcribed. A partial row is charged only for the minutes in its text

For developers

Sample result

One result from a real test run, in JSON. Real values change from run to run. In Excel or CSV each field is a column.

one result · JSON

{
  "sourceUrl": "https://www.archive.org/download/aesop_fables_volume_three_librivox/fables_03_01_aesop_64kb.mp3",
  "sourceType": "url",
  "podcastTitle": null,
  "title": null,
  "publishedAt": null,
  "episodeGuid": null,
  "episodeUrl": null,
  "status": "complete",
  "durationSec": 77.95,
  "transcribedSec": 77.95,
  "truncated": false,
  "language": "en",
  "languageProbability": 0.991,
  "task": "transcribe",
  "model": "base",
  "text": "This is a LibraVox recording. All LibraVox recordings are in the public domain. …",
  "wordCount": 161,
  "segments": [
    {"start": 0.75, "end": 3.65, "text": "This is a LibraVox recording."},
    {"start": 3.65, "end": 6.97, "text": "All LibraVox recordings are in the public domain."}
  ],
  "subtitles": null,
  "chargedMinutes": 2,
  "processingSec": 7.9,
  "error": null,
  "fetchedAt": "2026-10-13T14:43:36Z"
}

Use it from code

Actor ID: cliqtomedia/audio-video-transcriber. You need your Apify API token from Apify Console → Settings → API & Integrations.

Python · apify-client

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("cliqtomedia/audio-video-transcriber").call(run_input={
    "audioUrls": "[\"https://www.archive.org/download/aesop_fables_volume_three_librivox/fables_03_01_aeso…",
    "maxEpisodes": 3
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

cURL

curl -X POST "https://api.apify.com/v2/acts/cliqtomedia~audio-video-transcriber/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"audioUrls": "[\"https://www.archive.org/download/aesop_fables_volume_three_librivox/fables_03_01_aeso…", "maxEpisodes": 3}'

LangChain · langchain-apify

# pip install langchain-apify
# set APIFY_TOKEN in your environment
from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("cliqtomedia/audio-video-transcriber")
result = tool.invoke({"run_input": {"audioUrls": "[\"https://www.archive.org/download/aesop_fables_volume_three_librivox/fables_03_01_aeso…", "maxEpisodes": 3}})
print(result)

The cURL call waits for the results, up to 300 seconds. For longer runs, start a run (/runs) and get the results with a webhook or by checking the run. Apify API docs. LlamaIndex, MCP for AI agents and the JavaScript client: AI agents & MCP.

Data fields (23)

Field	Type	Meaning
`sourceUrl`	string	Media file URL (as given, or the RSS enclosure URL).
`sourceType`	string	url (from audioUrls), rss_episode (feed episode) or rss_feed (feed-level error row).
`podcastTitle`	string	Podcast name from the RSS feed.
`title`	string	Episode title from the RSS feed.
`publishedAt`	string	Episode publish date from the feed, ISO 8601 UTC.
`episodeGuid`	string	Episode GUID from the feed.
`episodeUrl`	string	Episode web page link from the feed.
`status`	string	complete (whole file), partial (only the first part was transcribed: duration limit, spending cap, time budget or an interrupted download), not_found (HTTP 404/410, feed without audio episodes) or error (see the error field).
`durationSec`	number	Media duration in seconds when known.
`transcribedSec`	number	Seconds of audio transcribed; charged minutes are this value rounded up to whole minutes.
`truncated`	boolean	true when only the first part of the file was transcribed.
`language`	string	Language code used (detected or chosen).
`languageProbability`	number	Confidence of language detection, 0–1.
`task`	string	transcribe or translate.
`model`	string	Whisper model used: tiny, base or small.
`text`	string	Full transcript text.
`wordCount`	integer	Words in text.
`segments`	array	Timed segments {start, end, text} in seconds; null when outputFormat is text.
`subtitles`	string	SRT or WebVTT file content when outputFormat is srt or vtt.
`chargedMinutes`	integer	Minutes charged for this file (0 on errors).
`processingSec`	number	Download, decode and transcription time in seconds.
`error`	object	{code, message}: e.g. NOT_FOUND, UNSUPPORTED_SOURCE, NOT_MEDIA, NO_AUDIO, FILE_TOO_LARGE, DOWNLOAD_TIMEOUT, TOO_SLOW, INVALID_FEED, TRUNCATED (partial), CHARGE_LIMIT, RUN_TIME_LIMIT, ABORTED and SKIPPED_SLOW_SOURCES (file skipped, not charged); null when none.
`fetchedAt`	string	When the row was produced, ISO 8601 UTC.

Input settings (8)

The main fields of the input form. With the API you send them as JSON.

Setting	Name in the API	Type	Example value
Audio or video file URLs	`audioUrls`	array	`["https://www.archive.org/download/aesop_fables_volume_three_librivox/fables_03_01_aeso…`
Podcast RSS feed URL	`podcastRssUrl`	string
Max episodes	`maxEpisodes`	integer	`3`
Model	`model`	string	`"base"`
Language	`language`	string	`"auto"`
Output format	`outputFormat`	string	`"segments"`
Translate to English	`translateToEnglish`	boolean	`false`
Max minutes per file	`maxDurationMinutes`	integer	`120`

Use cases with this tool

Each guide shows all the steps and the other tools.

One piece of content, ten new posts

Audio and Podcast Transcriber

How to use it: 3 steps

What it does

Good for

Not a good fit

Who uses it

Podcasters

Video makers

Researchers and students

Price

Examples

Questions

Details

For developers

Sample result

Use it from code

Use cases with this tool

Start on Apify

Audio and Podcast Transcriber

How to use it: 3 steps

What it does

Good for

Not a good fit

Who uses it

Podcasters

Video makers

Researchers and students

Price

Examples

Questions

Details

For developers

Sample result

Use it from code

Use cases with this tool

Similar tools

YouTube Subtitles & Transcript Scraper API

Apple Podcast Directory & RSS Contacts Scraper

YouTube Comments Scraper

Social Video Downloader: TikTok, Instagram, X - No Login

YouTube Search Results Scraper — No Login

Kick Live Streams & Viewer Count (Official API), No Login

Start on Apify