Audio & Video to Text: Podcast Transcript + On-Screen Text

Paste a link to a podcast episode, an audio file or a video, get back a timestamped transcript as clean JSON, plus the text shown on screen for videos. Each link also gets a ready-to-paste text block for ChatGPT, Claude, Gemini, or your own pipeline.

$0.005 per minute of media (a 1-hour podcast costs $0.30). You pay only for links processed successfully. No login, no API key of your own, no account anywhere.

What you can use it for

• Podcast transcripts. Turn episodes into searchable text for show notes, clips, quotes, SEO pages or research.
• AI agents and RAG. Feed audio and video into embeddings or a prompt. The llm_text field is one block per link.
• Meeting, lecture and interview recordings. Any public audio or video file link works: .mp3, .m4a, .wav, .mp4, .mov, .webm and more.
• Video research. For videos, on-screen text (slides, titles, burned-in captions, name tags) comes with timestamps next to the speech.

Why this Actor

	This Actor	Typical transcription Actor
Transcript with timestamps	Yes (Whisper large-v3-turbo, ~100 languages)	Yes
On-screen text for videos, with timestamps	Yes	No
Music / silence	Detected and skipped: no invented "Thank you." lines; speech_seconds tells you how much voice there is	Whisper-based tools may invent text on music
Long files	Up to 3 hours per link	Often 1 hour or less
Price	$0.005 per minute, no API key needed	$0.006-0.015 per minute, or bring your own key

Sample output

From a public TED Radio Hour episode (49.7 minutes; URL and lists shortened):

{
  "url": "https://.../npr.simplecastaudio.com/.../default.mp3",
  "platform": "generic",
  "duration_s": 2979.16,
  "language": "en",
  "speech_seconds": 2934.4,
  "hook": { "spoken": "This is the TED Radio Hour.", "on_screen": "" },
  "transcript": [
    { "start": 0.0, "end": 3.28, "text": "This is the TED Radio Hour." },
    { "start": 4.42, "end": 6.82, "text": "Each week, groundbreaking TED Talks." },
    { "start": 6.84, "end": 8.1, "text": "Our job now is to dream big." }
  ],
  "transcript_text": "This is the TED Radio Hour. Each week, groundbreaking TED Talks. Our job now is to dream big. ...",
  "on_screen_text": [],
  "llm_text": "VIDEO: https://.../default.mp3\n...\nTRANSCRIPT:\n[0:00.0] This is the TED Radio Hour.\n...",
  "status": "ok"
}

The full transcript of that episode is 7,373 words and took about 75 seconds.

Output fields

Field	Meaning
transcript	Spoken words as timestamped segments (seconds). Empty when there is no speech.
transcript_text	The transcript as one string.
on_screen_text	Videos only: text shown in the video with start/end (seconds), position (top/middle/bottom) and kind = caption (repeats the speech) or overlay (not spoken).
hook	What is said (and shown) in the first 3 seconds.
speech_seconds	Seconds of detected voice. Lets you filter music-only files.
duration_s	Length of the media in seconds (what the per-minute price is based on).
creator, caption, views, published_at	Filled when the page provides them (hosting pages); null for direct file links.
language	Detected spoken language (ISO code).
llm_text	Everything above as one plain-text block, ready to paste into an AI model.
status	ok, or error with an error message. Failed links are not charged.

How to use it

1. Paste one or more public links into Audio / video URLs:
   • a direct file link (https://.../episode.mp3, .mp4, .m4a, .wav ...);
   • a podcast episode: the audio URL from the show's RSS feed (the enclosure link). Feeds from NPR, Simplecast, Megaphone, Omny, Buzzsprout, Transistor, Spreaker, BBC and others were tested;
   • a page with an embedded video or audio, e.g. SoundCloud or Streamable.
2. Click Start.
3. Download the results as JSON, CSV or Excel, or read them through the Apify API, integrations (Make, Zapier, n8n) or the Apify MCP server for AI agents.

Input example:

{
  "urls": [
    "https://example.com/podcast/episode-42.mp3",
    "https://soundcloud.com/forss/flickermood"
  ]
}

Links are processed one after another within a run (a 50-minute episode takes about a minute). For large batches, split the links over several runs to process them in parallel.

Pricing

• $0.005 per started minute of media, only for links processed successfully (minimum 1 minute per link).
• Examples: 10-minute video = $0.05 · 1-hour podcast = $0.30 · 3-hour podcast = $0.90.
• Files longer than 3 hours are skipped and not charged. Failed links (private, deleted, login-only, unreachable) are not charged.
• Set Maximum cost per run in the run options to cap your spend. The Actor stops cleanly when the cap is reached.

Settings

Setting	Default	What it does
Audio / video URLs	(required)	Public links, one per line.
Read on-screen text	on	Videos only. Turn off if you only need the transcript.
Add llm_text field	on	One ready-to-paste text block per link.
Proxy configuration	automatic	Leave empty. The Actor uses Apify datacenter proxy and switches to residential automatically if a site blocks a request.

Limitations

• Public links only. Anything that needs a login, a paywall or DRM (Spotify, Apple Music, Netflix ...) cannot be processed and is not charged.
• Instagram, TikTok and Facebook links are not processed here: use the sister Actors Instagram Reels Transcript, TikTok Transcript and Facebook Reels Transcript (priced per video, with hooks and post stats).
• YouTube is not supported.
• Up to 3 hours per link.
• On-screen text is most accurate on designed text (titles, slides, captions). Text physically in the scene is read less reliably.
• Songs: lyrics may appear in the transcript; pure music returns an empty transcript.
• Need frames? Video Frame Extractor returns the key frames of video links as image URLs, each with its timestamp and the text visible on it ($2 per 1,000 frames).

FAQ

Do I need an account or API key anywhere? No. Speech-to-text is included in the price.

Which languages are supported? Speech in about 100 languages (Whisper large-v3-turbo). On-screen text is tuned for Latin-script text.

Is this legal? The Actor processes publicly available media and collects no personal data. You are responsible for how you use the output under the source's terms and the laws that apply to you (e.g. copyright, GDPR).

Something wrong with a result? Open an issue on the Actor's Issues tab with the link. Reliability fixes ship within 24 hours.