TED Video Transcript

Affiliate disclosure: Apify links on this page may include referral parameters. If you sign up through one of these links, TrueFetch may earn a commission from Apify at no extra cost to you. Pricing, features, and Actor access are unaffected.

TED Video Transcript converts one public TED talk or audio episode into detected-language text, timestamped segments, source metadata, and an optional translated transcript.

• The required input is one public ted.com/talks/... URL; talk catalogs, playlists, TED-Ed lessons, YouTube links, uploads, and cross-platform links are outside this Actor's scope.
• Each successful run returns one normalized Dataset record with 22 fields, including transcript text, segment timestamps, creator details, and source-provided engagement data.
• The optional translation selector contains 133 target languages and is charged only after every transcript segment is translated successfully.
• The platform precheck resolves the TED URL and confirms supported TED media before download and speech recognition begin.

Run a one-result test · View API

A smallest useful FREE-tier test uses the public TED episode already present in the input. It bills one $0.52 transcript event, the default 8 GB start charge of $0.008, and variable Actor usage. A completed translation adds $0.18.

What does TED Video Transcript do?

TED Video Transcript turns speech from one public TED talk or audio episode into detected-language text and ordered HH:MM:SS.mmm segments. Source metadata can include title, description, publisher, duration, thumbnail, play count, and tags.

Select a target under translate to receive a second transcript whose segments retain the source timing. The original detected-language result remains in transcript; the translated result appears in translation only after the complete translation succeeds.

It is not a TED catalog crawler, native-transcript exporter, bulk processor, speaker-diarization tool, media downloader, or subtitle-file generator. It handles one public talk-page URL per run.

How do I run TED Video Transcript?

1. Open TED Video Transcript on Apify.
2. Copy the canonical URL of one public TED talk or audio episode and paste it into Video URL.
3. Optionally select one Translate target. Leave it empty to return only the detected-language transcript.
4. Click Start and wait for media preparation and speech recognition to finish.
5. Review the single record in the default Dataset before exporting it or connecting another workflow.

The input schema currently pre-fills the TED Audio Collective episode below. The same example is used throughout this guide:

{
  "video_url": "https://www.ted.com/talks/ted_audio_collective_mystery_episode",
  "translate": "spanish"
}

One run represents one transcript job and one Dataset record. A URL may later expire or become unavailable.

What data does TED Video Transcript return?

The Actor writes one successful result to the default Dataset. Its 22-field contract is nullable where TED omits a value.

Group	Dataset fields	Meaning
Processing	processor, processed_at	Actor URL and UTC processing time
TED source	platform, title, description, thumbnail, published_at	Talk or episode identity, text, image, and publishing time
Creator	author, author_id, author_url	Creator details exposed for the media
Media	duration, audio_title, audio_artist	Source-reported length and audio attribution
Engagement	view_count, like_count, shares_count, dislike_count, comment_count	Counts exposed by the current extraction path
Labels	categories, tags	Source-provided classifications when available
Speech	transcript, translation	Original timestamped transcript and optional translated version

This abbreviated response uses the same TED-episode-and-Spanish scenario. Values omitted by TED remain null, zero, or empty; the Actor does not invent them.

{
  "processor": "https://apify.com/truefetch/ted-video-transcript?fpr=aiagentapi",
  "processed_at": "2026-07-21T13:03:48+00:00",
  "platform": "TedTalk",
  "title": "Mystery episode",
  "description": null,
  "author": "TED Audio Collective",
  "duration": 55,
  "view_count": 1177355,
  "tags": ["storytelling", "creativity"],
  "transcript": {
    "language": "English",
    "text": "Hi, TED Talks Daily listener. We've been sharing podcasts from the TED Audio Collective.",
    "segments": [
      {
        "start": "00:00:04.219",
        "end": "00:00:13.890",
        "text": "Hi, TED Talks Daily listener. We've been sharing podcasts from the TED Audio Collective."
      }
    ]
  },
  "translation": {
    "language": "Spanish",
    "text": "Hola, oyente de TED Talks Daily. Hemos estado compartiendo pódcasts del TED Audio Collective.",
    "segments": [
      {
        "start": "00:00:04.219",
        "end": "00:00:13.890",
        "text": "Hola, oyente de TED Talks Daily. Hemos estado compartiendo pódcasts del TED Audio Collective."
      }
    ]
  }
}

The Dataset does not include a status field, source video file, SRT or VTT file, summary, confidence score, speaker identity, private account data, or word-level timeline.

What inputs can I configure?

Input	Type	Required	Behavior
video_url	string	Yes	One public TED talk or audio-episode URL.
translate	string enum	No	One of 133 target-language values. Empty means no translation.

video_url must resolve to public media through the TED extraction path. There are no inputs for cookies, credentials, uploads, usernames, profiles, date filters, or URL lists.

Translation values are lowercase language names such as spanish, french, japanese, arabic, chinese (simplified), and chinese (traditional). Translation does not replace the detected source language or alter the original transcript object.

What platforms and markets does TED Video Transcript cover?

This TED-only Actor accepts a canonical public ted.com/talks/{slug} page. TED explains that its talk library normally exposes interactive transcripts, but this Actor independently transcribes playable media into the common Dataset contract.

Before running the Actor, confirm that your intended use is permitted. TED's Terms of Use restrict automated access, scraping, and use of TED content in AI workflows without appropriate permission, while the TED Talks Usage Policy describes separate licensing limits. A public page is not proof that every automated or commercial use is authorized.

Removed, unavailable, restricted, or malformed talk pages, catalog pages, playlists, TED-Ed lesson pages, YouTube URLs, and pages without playable media are not promised.

Speech language is detected from audio. Review generated text and translation for names, slang, accents, brand terms, and code-switching.

Why use TED Video Transcript?

Verified capability	Practical benefit
TED-specific platform validation	Reject unrelated platform links before transcription begins.
Full text plus timestamped segments	Search what was said while retaining time ranges for review.
Source metadata beside the transcript	Keep creator, duration, thumbnail, publication time, and available counts with the speech.
Optional timestamp-preserving translation	Review the same TED talk in another language without losing the original transcript.
One normalized Dataset record	Connect a predictable object to editorial, research, moderation, or AI workflows.

TED may change public data, and speech recognition may mishear names, overlapping voices, music, or specialized vocabulary. Review quotations, captions, translations, and high-stakes conclusions.

Who is TED Video Transcript for?

The Actor serves developers, educators, journalists, researchers, content teams, and AI builders with a specific public TED page. Typical uses include searching talks, reviewing arguments, drafting translations, and supplying timed text downstream.

Choose another product for feed discovery, private content, comments, downloaded media, on-screen text recognition, legal transcripts, live monitoring, or non-TED sources.

How can I use TED Video Transcript through the API or MCP?

The public Actor identifier is truefetch/ted-video-transcript. Use an asynchronous Actor run for longer media or workflows that should not hold one HTTP connection open. Apify documents that synchronous Dataset responses can return HTTP 408 after 300 seconds even when a run continues.

curl -L "https://api.apify.com/v2/actors/truefetch~ted-video-transcript/run-sync-get-dataset-items" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://www.ted.com/talks/ted_audio_collective_mystery_episode",
    "translate": "spanish"
  }'

Apify's hosted MCP server can expose only this Actor to a compatible client:

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com?tools=truefetch/ted-video-transcript",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

Call truefetch/ted-video-transcript with the same URL and spanish. See the Apify MCP guide and Actor API page.

How much does TED Video Transcript cost?

TED Video Transcript uses pay-per-event pricing. Confirm the live pricing page before a large or scheduled workload because Store prices can change.

Billed event	FREE	BRONZE	SILVER	GOLD	PLATINUM	DIAMOND	Billing unit
Actor start	$0.001	$0.001	$0.001	$0.001	$0.001	$0.001	One event per allocated GB, minimum one
Actor usage	$0.00001	$0.00001	$0.00001	$0.00001	$0.00001	$0.00001	Runtime, proxy, and storage usage unit
Transcript	$0.52000	$0.50267	$0.48533	$0.46800	$0.46800	$0.46800	One successful timestamped transcript
Translation	$0.18000	$0.17400	$0.16800	$0.16200	$0.16200	$0.16200	One complete translated transcript when requested

Smallest FREE-tier calculation: the default 8 GB run creates eight start events, so $0.001 × 8 + $0.52000 = $0.528, plus variable Actor usage. A completed Spanish translation makes the fixed-event subtotal $0.708, plus usage. Use Apify's maxTotalChargeUsd run option when an automated workload needs a spending ceiling.

How does TED Video Transcript compare with alternatives?

Option	Best fit	Trade-off
TED Video Transcript	One known TED talk or audio episode, normalized text, timestamps, and source context	One item per run; no catalog crawling, media file, or speaker labels
TED's interactive transcript	Reading and navigating the native transcript on the TED page	Not the same normalized Dataset/API contract; availability and languages are source-controlled
Universal video-to-text Actor	Mixed platforms or uploaded media	Less narrowly guided TED input experience
Manual transcription	Sensitive quotations requiring human judgment	More time and coordination for timestamps and translation

Use this Actor when the spoken content is the primary deliverable. Choose Video To Text for uploads or other platforms, and Best Video Downloader when the required result is the media file rather than transcript data.

What are the limits and troubleshooting steps?

Symptom or limit	What it means	Next step
The Actor rejects the platform	The URL does not resolve as supported TED media	Copy the canonical ted.com/talks/{slug} URL
Video information cannot be retrieved	The page is removed, restricted, malformed, or temporarily unavailable	Confirm its media plays publicly and retry
The media has no usable speech	Audio is absent, silent, music-only, or too unclear for speech detection	Test a short TED video with clear dialogue
Metadata is empty or duration is 0	TED did not expose that creator, timing, publishing, or view value	Treat source fields as optional; do not infer missing values
Translation is absent	One or more transcript segments did not translate completely	Keep the original transcript and retry; incomplete translation is not charged
A synchronous API call returns HTTP 408	The request exceeded Apify's documented synchronous response window	Start asynchronously, poll the run, then read the Dataset

Segment boundaries are ordered but are not word-level timestamps. Never post a private token or confidential media in an issue. Share the run ID, the smallest public reproduction URL, the expected behavior, and the visible error.

Frequently asked questions

Can it process the TED talk catalog or a playlist?

No. The supported contract is one specific public TED talk-page URL per run.

Can it process TED-Ed or YouTube URLs?

No. Those resolve to different platforms or page types. Use the canonical supported TED talk URL.

Does it copy TED's existing interactive transcript?

No. It generates transcript text from audible media and does not export TED's native transcript, SRT, or VTT file.

Can it process an audio-only TED page?

It can process a supported public TED page when the current extraction path exposes playable audio. Availability and media access are checked at run time.

Why are description, thumbnail, or creator ID empty?

Those values depend on what TED exposes for that exact page. The Dataset keeps them nullable instead of inventing a value.

Is translation billed if one segment fails?

No. A translation event is charged only after a complete translated transcript is attached to the result.

Can I use segment timestamps as finished subtitles?

They are useful time ranges for downstream processing, but the Actor does not create a subtitle file or guarantee word-level alignment. Review them before publication.

Can I schedule the same TED talk URL repeatedly?

Yes. Apify schedules can rerun saved input. Each successful run is independently billed, and public availability or metadata may change between runs.

Related TrueFetch Actors

• Video To Text accepts uploaded media and public URLs from many platforms when a TED-only contract is too narrow.
• Instagram Video Transcript provides the same timestamped-transcript workflow for public Instagram video posts.
• Best Video Downloader is the better fit when the required deliverable is a downloadable media file.

Support and last updated

• Actor page and documentation
• API reference and generated clients
• Issues
• TrueFetch community
• Direct support

The local input, Dataset, output, and pricing metadata plus the cited official documentation links were reviewed on July 21, 2026. TED media availability and online Store information are volatile and may change after that date.

Run a one-result test · View API