Podcast Transcript Generator & API: Audio & Video to Text

Podcast Transcript Generator & API: Audio & Video to Text

Turn podcasts and audio / video files into text: paste an Apple Podcasts or Spotify link, an RSS feed, a podcast's name, or any MP3, M4A, WAV, MP4 or MOV link. You get the full transcript, speakers, timed segments and ready SRT and VTT subtitles, with the episode's title, date and length.

Many podcasts publish their own transcript with each episode, often with speaker names. The Actor uses that transcript whenever it exists (instant, any length, $0.00199 an episode). Everything else is transcribed from the audio by Whisper AI in 99 languages at $0.00599 per minute. Files without speech are free.

{ "sources": ["https://podcasts.apple.com/us/podcast/stuff-you-should-know/id278981407", "Darknet Diaries", "https://example.com/interview.mp3"], "maxEpisodes": 3 }

No sign-up on a transcription website, no API key, no upload limits: use it as a transcription API for a single file or for whole podcasts.

What you get

One row per file or episode. Real example, October 2026:

podcastTitle	episodeTitle	transcriptSource	language	speakers	wordCount	durationSeconds	aiMinutes
Stuff You Should Know	The Twilight Zone Episode	podcast-feed	en	Speaker 1, Speaker 2	8,756	2,760	0
Darknet Diaries	181: Ricky	podcast-feed	en	JACK	15,329	4,815	0
NPR News Now	7am ET, October 23	ai	en		740	303	6

Field	Description
transcript	The spoken words as one text; with speakers, a paragraph per speaker turn ("JACK: ...")
segments	[{start, end, text, speaker}] with seconds, for quotes, clips, chapters and search inside an episode
subtitlesSrt, subtitlesVtt	Ready subtitles for a video editor, YouTube or a player
srtFileUrl, vttFileUrl, txtFileUrl	Download links of the same as files (with Save files)
speakers	Speaker names when the podcast's transcript has them
transcriptSource	podcast-feed (the transcript the podcast publishes) or ai (Whisper speech recognition)
transcriptionModel, aiMinutes	Which transcript or model wrote the text, and the AI minutes charged
language, languageName	Spoken language: en / English
wordCount, segmentCount, speechSeconds, hasTimestamps	How much is said, and for how long
podcastTitle, podcastAuthor, episodeTitle, season, episodeNumber, publishedAt, durationSeconds, imageUrl	The podcast and the episode
episodeUrl, audioUrl, feedUrl, publishedTranscriptTypes	Links: the episode page, the audio file, the RSS feed, and the transcript formats the podcast publishes
hasTranscript, noTranscriptReason	false with the reason when a file has no speech or was skipped (free)
input, inputType, position, scrapedAt, error	Which input the row came from; why a file was not read

What you can paste

Input	What happens
Audio / video file link	.mp3, .m4a, .wav, .ogg, .opus, .flac, .aac, .mp4, .mov, .webm, .mkv... up to 1.5 GB and 10 hours
Dropbox / Google Drive share link	Turned into a direct download (the file must be shared with "anyone with the link")
Web page with a player	The page's audio or video file (og:audio, <audio>, <video>, a link to an .mp3); a podcast website's episode page is found in its feed
Podcast RSS feed	The latest episodes (Episodes per podcast)
Apple Podcasts link	A show (latest episodes) or one episode (?i=...)
Spotify link	A show or an episode, found in the podcast's public feed. Spotify-only shows have no public audio and cannot be transcribed
Podcast name	"Lex Fridman Podcast", "The Daily": found on Apple Podcasts

YouTube, TikTok, Instagram and Facebook links are not files: use our YouTube Transcript Scraper, TikTok Transcript Scraper, Instagram Reel Transcript or Facebook Video Transcript.

Settings

Setting	What it does
Episodes per podcast	Latest N episodes of each podcast (default 1, 0 = all of them)
Only episodes published after	Only recent episodes: 2026-10-01 or 7 days, 2 weeks, 1 month
Only new episodes	Skip what earlier runs already saw: schedule it to follow podcasts
Use the podcast's own transcript	On by default. Off = every file goes through AI
Transcribe with AI	On by default. Off = only published transcripts, the rest are free rows
Spoken language	Empty = detected from each file's first minutes. Set en, es, de... only if detection picks the wrong one
Max file length	Longer files are skipped for free (default 300 minutes)
Timed segments / SRT and VTT / Save files	What goes into each row, and .srt .vtt .txt files in your storage

Why this Actor

📄 Published transcripts first	About 1 in 4 big podcasts publish a transcript in their feed (Stuff You Should Know, The Diary of a CEO, Darknet Diaries, Acquired, every Buzzsprout show with transcripts on): you get it with speaker names for a flat $0.00199, whatever the length
🤖 Whisper AI for everything else	$0.00599 a minute, 99 languages, language detected automatically; a voice detector runs first, so music and silence are not transcribed and AI never invents words over a jingle
🔗 Any link	Apple Podcasts, Spotify, RSS, podcast names, direct files, Dropbox, Google Drive, web pages with a player: no need to find the MP3 yourself
⏱️ Long files	Episodes of 3-5 hours are cut into 10-minute pieces at pauses, so no word is split and memory stays low
🔔 Podcast monitoring	Only the new episodes since the last run, on a schedule

Follow podcasts automatically

1. Add the podcasts you follow (names, Apple or Spotify links, or RSS feeds)
2. Turn on Only new episodes
3. Save as a task with a daily schedule: each run transcribes only the new episodes, ready for a Google Sheet, Slack, a newsletter or an AI summary through an integration

The list of seen episodes is kept per podcast and monitor name in your account (key-value store audio-transcriber-state).

Pricing

Pay per AI minute, or a flat price for an episode whose podcast publishes its transcript. Apify Scale and Business plans pay less:

Event	Free and Starter plans	Scale plan	Business plan
Run start	$0.001	$0.001	$0.001
Audio minute transcribed by AI (started minutes, rounded up per file)	$0.00599	$0.00539	$0.00479
Published podcast transcript, per episode (any length)	$0.00199	$0.00179	$0.00159

Task	Cost
A 5-minute voice memo or news bulletin	~$0.03
A 1-hour podcast episode without a published transcript	~$0.36
A 1-hour episode of a podcast that publishes transcripts	~$0.002
100 hours of interviews	~$36
Following a weekly 1-hour podcast for a month	~$1.45 per month

Files without speech, files that are not found and files over the length limit are not charged.

Ready-made tasks

Open it, change the link, and run:

Task	What you get
Podcast Transcript Generator from Link: Spotify, Apple, RSS	Transcripts of the podcast episodes you paste, with speakers and SRT

FAQ

How do I get the transcript of a podcast episode? Paste the episode's Apple Podcasts or Spotify link (or the podcast's name for its latest episode) into Audio / video links, podcasts and run. The transcript column has the text; subtitlesSrt has it with timestamps.

Where does the text come from? From the transcript the podcast publishes in its RSS feed when there is one (transcriptSource: podcast-feed): made by the podcast or its hosting service, usually with speaker names. Otherwise from OpenAI's Whisper speech recognition (transcriptSource: ai): large-v3-turbo, or Whisper base when the hosted model is busy. Clear speech comes out nearly word for word; names, jargon and crosstalk can be misheard.

Can I transcribe Spotify podcasts? Yes, when the podcast is also published outside Spotify (nearly all are): the Actor finds the same episode in the podcast's public feed. Spotify-only shows and paid episodes have no public audio file.

Which languages are supported? The 99 languages of Whisper, detected for each file. Published transcripts come in the podcast's language.

Does it identify speakers? Published transcripts usually include speaker names (speakers, and speaker in each segment). AI transcripts do not separate speakers.

How are AI minutes counted? By the file's length, rounded up once per file: a 40-second clip is 1 minute, a 61-minute episode is 62. Published transcripts have no AI minutes.

How long does a long episode take? About 1-3 minutes per hour of audio while the hosted model is available, up to ~15 minutes per hour on the fallback model. Raise the run's memory to make the fallback faster.

Can I upload a file from my computer? Upload it anywhere that gives a public link (Dropbox, Google Drive, an Apify key-value store, your website) and paste that link.

Use with the API and AI agents

Run it via the Apify API from Python, Node.js or any HTTP client, or connect it to Claude, ChatGPT and other AI agents through the Apify MCP server: "Transcribe the last 3 episodes of Acquired and summarise what they say about Nvidia".

Other transcript tools

Tool	What it does
YouTube Transcript Scraper	YouTube captions of videos, channels and playlists in any language
TikTok Transcript Scraper	TikTok subtitles and AI transcripts from links or profiles, SRT and VTT
Instagram Reel Transcript	Instagram Reels to text from links or profiles, SRT and VTT
Facebook Video Transcript	Facebook videos and Reels to text, Facebook captions or AI

Is it legal?

The Actor reads only public files and feeds that anyone can open, without logging in. Transcripts are the speakers' words: use them for research, accessibility, notes or quotes in line with copyright law, and handle personal data such as names in line with GDPR and other privacy laws.