Linkedin Video Transcript avatar

Linkedin Video Transcript

Pricing

from $0.423 / transcript

Go to Apify Store
Linkedin Video Transcript

Linkedin Video Transcript

LinkedIn Video Transcript converts one public LinkedIn video post into text for webinar notes, executive quotes, and B2B content research. Output includes detected language, ordered timestamps, post metadata, and optional translation into 133 languages. Transcripts begin at $0.423.

Pricing

from $0.423 / transcript

Rating

0.0

(0)

Developer

TrueFetch

TrueFetch

Maintained by Community

Actor stats

0

Bookmarked

3

Total users

2

Monthly active users

3 days ago

Last modified

Share

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.

Linkedin Video Transcript converts one public LinkedIn video post into detected-language text, timestamped segments, post metadata, and an optional translated transcript.

  • The required input is one public LinkedIn video-post URL; profiles, private posts, non-video posts, uploads, and cross-platform links are outside this Actor's scope.
  • One completed post creates one 22-field Dataset item combining the spoken message, time ranges, author context, and any post metrics LinkedIn exposes.
  • The translation menu offers 133 targets; billing occurs only after every original segment has a corresponding translated segment.
  • Before downloading media, the URL precheck resolves the post and confirms that yt-dlp identifies a LinkedIn extractor.

Run a one-result test · View API

Use the prefilled public post for a small FREE-tier trial. Its fixed events are a $0.47 transcript and an $0.008 start for the default 8 GB allocation, followed by variable usage. A complete translated copy adds $0.15.

What does Linkedin Video Transcript do?

Linkedin Video Transcript turns speech from one public LinkedIn video post into detected-language text and ordered HH:MM:SS.mmm segments. When exposed, post metadata can include title, description, creator, duration, thumbnail, publishing time, audio attribution, and engagement counts.

When translate is set, the Actor keeps recognition output in transcript and builds a second object in the chosen language. Segment order and time ranges remain paired with the original; an incomplete conversion is not published.

This Actor does not search the LinkedIn feed, open private posts or messages, crawl profiles, process URL batches, label speakers, export video, read on-screen text, or create subtitle files. Its unit of work is one known public video post.

How do I run Linkedin Video Transcript?

  1. Open Linkedin Video Transcript on Apify.
  2. Copy the canonical URL of one public LinkedIn video post and paste it into Video URL.
  3. Select Translate only if the post needs a second-language rendering; leave it unset for source speech alone.
  4. Click Start and wait for media preparation and speech recognition to finish.
  5. Check the resulting Dataset item for names, nullable post fields, and segment timing before reuse.

Start with a LinkedIn post whose native video contains clear dialogue. The current input schema supplies this example URL:

{
"video_url": "https://www.linkedin.com/posts/adam-r-kett-b09757396_my-first-video-is-out-it-feels-good-to-finally-activity-7396562269847072768-vlSN",
"translate": "spanish"
}

The run does not expand beyond that post. It produces at most one record, and the source link can later become restricted, edited, or unavailable.

What data does Linkedin Video Transcript return?

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

GroupDataset fieldsMeaning
Processingprocessor, processed_atActor URL and UTC processing time
LinkedIn video postplatform, title, description, thumbnail, published_atSource identity, text, image, and publishing time
Creatorauthor, author_id, author_urlCreator details exposed for the media
Mediaduration, audio_title, audio_artistSource-reported length and audio attribution
Engagementview_count, like_count, shares_count, dislike_count, comment_countPost counters returned by LinkedIn's public response; absent values remain nullable
Labelscategories, tagsSource-provided classifications when available
Speechtranscript, translationOriginal timestamped transcript and optional translated version

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

{
"processor": "https://apify.com/truefetch/linkedin-video-transcript?fpr=aiagentapi",
"processed_at": "2026-07-21T12:42:13+00:00",
"platform": "LinkedIn",
"title": "My first video is out",
"description": "I’m here to share what we’re building, what we’re learning, and how tech is reshaping the way we work.",
"author": null,
"duration": 0,
"like_count": 10,
"transcript": {
"language": "English",
"text": "Hey, nice to meet you. My name is Adam. I am the first AI employee from Rocket Force Solutions.",
"segments": [
{
"start": "00:00:00.000",
"end": "00:00:09.830",
"text": "Hey, nice to meet you. My name is Adam. I am the first AI employee from Rocket Force Solutions."
}
]
},
"translation": {
"language": "Spanish",
"text": "Hola, encantado de conocerte. Me llamo Adam. Soy el primer empleado de IA de Rocket Force Solutions.",
"segments": [
{
"start": "00:00:00.000",
"end": "00:00:09.830",
"text": "Hola, encantado de conocerte. Me llamo Adam. Soy el primer empleado de IA de Rocket Force Solutions."
}
]
}
}

The output contract excludes the media file, profile or private-account data, summaries, confidence values, named speakers, SRT/VTT downloads, and per-word timing. Consumers should not infer those artifacts from the segment array.

What inputs can I configure?

InputTypeRequiredBehavior
video_urlstringYesOne public LinkedIn video-post URL.
translatestring enumNoOne of 133 target-language values. Empty means no translation.

video_url must lead directly to a publicly viewable LinkedIn post with native video. No form control accepts credentials, session cookies, file uploads, member names, profile searches, time filters, or a list of posts.

Language choices are lowercase labels such as spanish, french, arabic, japanese, chinese (simplified), and chinese (traditional). The selected value creates a companion result; it never changes transcript.

What platforms and markets does Linkedin Video Transcript cover?

This LinkedIn-only Actor expects the canonical URL of a public post containing native video. LinkedIn's official help explains how to copy the unique link assigned to shared content.

Private or connections-only posts, messages, deleted posts, profile pages, articles without native video, login-gated content, and unsupported links are not promised. Public access may change later.

Detection follows the audio track rather than the written post. Review company names, people, abbreviations, technical terms, accents, and mixed-language speech before relying on the text.

Use only material you are authorized to process and review the current LinkedIn User Agreement for the intended workflow.

Why use Linkedin Video Transcript?

Verified capabilityPractical benefit
LinkedIn-specific platform validationReject unrelated platform links before transcription begins.
Full text plus timestamped segmentsSearch what was said while retaining time ranges for review.
Post context beside recognized speechPreserve the available author, description, thumbnail, date, duration, and counters for later analysis.
Translation aligned to speech segmentsCompare a target-language version with the original professional presentation without changing its timing.
One object for one selected postPass a stable record to recruiting research, editorial review, sales enablement, or an AI workflow.

LinkedIn controls whether a post remains public and which fields it reveals. Speech recognition can still confuse names, acronyms, overlapping voices, and background music, so machine text is not a final quotation source.

Who is Linkedin Video Transcript for?

The Actor serves developers, social teams, recruiters, journalists, researchers, and AI builders with a specific public video post. Typical uses include searching presentations, comparing speech with post text, drafting translations, and supplying timed text downstream.

Choose a different tool for discovering posts, accessing member-only content, collecting comment threads, downloading the video, extracting text from frames, preparing legal transcripts, monitoring live media, or handling another network.

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

Call the Actor by truefetch/linkedin-video-transcript. A synchronous Dataset response is convenient for a brief post, while durable integrations should start the run asynchronously and poll its state. Apify documents that an HTTP wait can end even though the Actor is still running.

curl -L "https://api.apify.com/v2/actors/truefetch~linkedin-video-transcript/run-sync-get-dataset-items" \
-H "Authorization: Bearer YOUR_APIFY_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"video_url": "https://www.linkedin.com/posts/adam-r-kett-b09757396_my-first-video-is-out-it-feels-good-to-finally-activity-7396562269847072768-vlSN",
"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/linkedin-video-transcript",
"headers": {
"Authorization": "Bearer YOUR_APIFY_TOKEN"
}
}
}
}

After MCP setup, send the post URL and spanish to truefetch/linkedin-video-transcript, then read the single Dataset result. Follow the Apify MCP guide for authentication and the Actor API page for generated clients.

How much does Linkedin Video Transcript cost?

Charges are split among run start, resource consumption, transcript completion, and optional translation completion. These local metadata values should be compared with the live pricing page before committing a large recurring workload.

Billed eventFREEBRONZESILVERGOLDPLATINUMDIAMONDBilling unit
Actor start$0.001$0.001$0.001$0.001$0.001$0.001One event per allocated GB, minimum one
Actor usage$0.00001$0.00001$0.00001$0.00001$0.00001$0.00001Runtime, proxy, and storage usage unit
Transcript$0.47000$0.45433$0.43867$0.42300$0.42300$0.42300One successful timestamped transcript
Translation$0.15000$0.14500$0.14000$0.13500$0.13500$0.13500One complete translated transcript when requested

For FREE-tier arithmetic, eight start units at $0.001 cover the default 8 GB allocation. One $0.47000 transcript makes the fixed subtotal $0.478; a completed $0.15000 Spanish translation raises it to $0.628, before usage. Set maxTotalChargeUsd for a hard automation ceiling.

How does Linkedin Video Transcript compare with alternatives?

OptionBest fitTrade-off
Linkedin Video TranscriptConverting the spoken content of a selected public professional post into timed textRequires a known native-video post and does not discover feed content
General LinkedIn scraperCollecting profiles, post text, comments, or network metadataAudio recognition is usually not its primary output
Universal video-to-text ActorSending uploaded media or URLs from several platforms through one contractOffers less guidance for LinkedIn post URLs
Human transcriptionApproving sensitive executive or employment-related quotationsCosts more time but supplies editorial judgment

Use this Actor for dialogue in one known LinkedIn post. Send uploaded recordings or other sites to Video To Text; choose Best Video Downloader when the actual deliverable is the video asset.

What are the limits and troubleshooting steps?

Symptom or limitWhat it meansNext step
The Actor rejects the platformThe URL does not resolve as a supported LinkedIn video postCopy the canonical public /posts/ URL from LinkedIn
Video information cannot be retrievedThe post is restricted, deleted, changed, or not publicly visible outside LinkedInTest the copied post link in a logged-out browser before retrying
The media has no usable speechNative audio is missing, silent, music-only, or unclearSelect a post with intelligible spoken presentation
Metadata is empty or duration is 0LinkedIn omitted that author, audio, date, timing, or engagement fieldKeep the documented nullable value instead of guessing
Translation is absentTranslation did not complete for the whole transcriptRetain the source result and retry if needed; no partial translation is charged
A synchronous API call returns HTTP 408The HTTP response window closed before processing endedPoll an asynchronous run and retrieve its Dataset after success

Segments identify phrase-level intervals, not exact word cues. Support reports should omit access tokens and confidential company media, but include the run ID, a public reproduction post, expected output, and observed error.

Frequently asked questions

Can it process a private post, chat, or Story?

No. The input has no credential or cookie field. Use one publicly accessible LinkedIn video media URL.

Can it crawl a creator profile or LinkedIn video feed?

No. The production contract is one specific LinkedIn video post per run, not discovery or batch crawling.

Does it use existing LinkedIn captions?

The Actor listens to the post's audio instead of copying LinkedIn captions. It returns JSON speech segments, not text burned into frames or an SRT/VTT download.

What happens when a LinkedIn video contains only music?

A silent presentation or music-only clip can produce a no-speech response. Pick a post with clearly audible words when text is required.

Why are likes, comments, audio attribution, or creator ID empty?

LinkedIn's public response varies by post. The schema represents omitted author or engagement information with nullable values rather than estimates.

Is translation billed if one segment fails?

No. The translated object must contain the complete segment sequence before its event is charged.

Can I use segment timestamps as finished subtitles?

They help locate passages and draft captions, but they are phrase ranges. Publication-ready subtitles still need review and formatting outside this Actor.

Can I schedule the same LinkedIn video URL repeatedly?

Yes. An Apify schedule can reuse the post URL; every execution is billed separately, and later runs may see different visibility or metadata.

  • Video To Text accepts files and links outside LinkedIn when a platform-specific form is too restrictive.
  • Instagram Video Transcript provides the same timestamped-transcript workflow for public Instagram Reels and video posts.
  • Best Video Downloader is the better fit when the expected output is a downloadable media file instead of transcript data.

Support and last updated

Local schema, extractor behavior, metadata pricing, and cited documentation were checked on July 21, 2026. LinkedIn controls future post visibility and exposed fields.

Run a one-result test · View API