Loom Transcript - Timestamped Loom Speech-to-Text API

Loom Transcript converts one public Loom share video into detected-language text, ordered timestamped segments, source metadata, and an optional translated transcript. It processes audible speech from the media; it does not promise to return Loom caption tracks or existing subtitle files.

• Input is one Loom /share/{id} recording whose link setting allows anyone with the link to view it.
• The precheck follows the share URL and confirms Loom media before download and speech recognition start.
• A completed recording produces one 22-field Dataset item containing available recording context and ordered speech segments.
• Workspace-only, invited-viewer, password-protected, deleted, or otherwise restricted Looms are not opened with credentials.

Run Loom Transcript · Open the API page

Use a recording you own or are authorized to process, confirm its link is publicly viewable, and review the generated transcript before connecting it to documentation automation.

---

Why Choose This API

A narrow contract for one known Loom video

This Actor fits a known Loom share link, such as a product walkthrough, async update, or support explanation, when the audio must become structured text. One URL and one optional target language form the entire public input. Extractor identity, not the hostname string alone, makes the final platform decision.

The result combines source context and spoken content in one record:

Capability	What is returned
Recording speech	Detected language, full text, and ordered start / end / text ranges
Loom context	Title, description, recorder identifiers, duration, publication time, thumbnail, categories, and tags when available
Exposed activity	Views and any supported nullable engagement fields returned by the extractor
Optional translation	A complete second-language segment list retaining source timing

It does not enumerate a Loom workspace, process a folder, bypass share settings, export Loom's own transcript/comments/chapters, identify speakers, summarize the recording, or return its video file. Absent source fields stay null, zero, or empty.

The recording's audio drives recognition. Screen text, cursor actions, and slides are not read. Microphone quality, system-audio balance, accents, crosstalk, and company terminology can affect accuracy, so review operational instructions before reuse.

---

Quick Start Guide

Run in Apify Console

1. Open Loom Transcript on Apify.
2. In Loom, set the recording to Anyone with the link, copy its /share/ URL, and paste it into Video URL.
3. Choose Translate only when one localized copy is required.
4. Start the run and review the single Dataset item after completion.

The schema currently pre-fills this Loom share link:

{
  "video_url": "https://www.loom.com/share/c43a642f815f4378b6f80a889bb73d8d",
  "translate": "spanish"
}

The API and response sections reuse that ID for consistency. A recording owner can delete it or change sharing to workspace-only, specific people, or password-protected access. Replace an unavailable example with another authorized recording set to public link access.

What success means

A valid transcript requires a viewable share link, media with audio, detected speech, and one published Dataset object. Loading the share page or reading its title is not enough.

---

Input Parameters

Input configuration

Input	Type	Required	Description
video_url	string	Yes	One public Loom video URL to download and transcribe.
translate	string	No	One target language from the schema's 133 selectable values. Leave empty to skip translation.

One run processes one share ID. Workspace homepages, libraries, folders, user pages, restricted recordings, password-protected links, uploads, cookies, credentials, and URL arrays are not accepted. The downloader never expands a collection.

A correct /share/ format can still fail when link settings change, the recording is deleted, a password is added, Atlassian changes delivery, or no usable audio stream is exposed.

Translation begins only after source segments exist. Workers can run concurrently but output order follows the recording. Any final segment failure removes the optional translation and its charge rather than returning a partial structure.

---

Output Data Schema

One 22-field Dataset item

A successfully transcribed Loom produces one 22-field Dataset record:

Group	Fields	Notes
Processing	processor, processed_at	Actor URL and processing timestamp
Identity	platform, title, description, thumbnail, published_at	Source-provided video identity
Author	author, author_id, author_url	Channel or uploader context when available
Media	duration, audio_title, audio_artist	Source-reported values; duration can be 0 when metadata is absent
Engagement	view_count, like_count, shares_count, dislike_count, comment_count	Nullable source metrics
Labels	categories, tags	Source classifications when exposed
Speech	transcript, translation	Timestamped source transcript and optional translated version

Abbreviated schema illustration for the Loom-and-Spanish example:

{
  "processor": "https://apify.com/agentx/loom-transcript?fpr=aiagentapi",
  "processed_at": "2026-07-21T13:30:00+00:00",
  "platform": "Loom",
  "title": "Lilah Nielsen Intro Video",
  "author": "Lilah Nielsen",
    "duration": 20,
    "categories": [],
  "tags": [],
  "transcript": {
    "language": "English",
    "text": "Hi there, hope everyone's having a great day.",
    "segments": [
      {
        "start": "00:00:00.320",
        "end": "00:00:08.519",
        "text": "Hi there, hope everyone's having a great day."
      }
    ]
  },
  "translation": {
    "language": "Spanish",
    "text": "Hola, espero que todos estén teniendo un gran día.",
    "segments": [
      {
        "start": "00:00:00.320",
        "end": "00:00:08.519",
        "text": "Hola, espero que todos estén teniendo un gran día."
      }
    ]
  }
}

Example values are illustrative snapshots. The Dataset does not add the video file, Loom's native transcript, comments, chapters, screen OCR, speaker identities, word timing, confidence, summaries, or legal verification.

---

Integration Examples

REST API

The synchronous endpoint returns Dataset items directly:

curl -L "https://api.apify.com/v2/actors/agentx~loom-transcript/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://www.loom.com/share/c43a642f815f4378b6f80a889bb73d8d",
    "translate": "spanish"
  }'

For long videos or workflows that must not hold one HTTP connection open, start an asynchronous run and retrieve its Dataset afterward. Apify documents that synchronous Dataset responses can time out after 300 seconds while the Actor run continues.

Python client

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("agentx/loom-transcript").call(
    run_input={
        "video_url": "https://www.loom.com/share/c43a642f815f4378b6f80a889bb73d8d",
        "translate": "spanish",
    }
)
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item["transcript"]["text"])

MCP for AI clients

Configure the Apify MCP server with the Actor-scoped tool URL:

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

Call agentx/loom-transcript with the same input fields. See the Apify MCP documentation and the generated Actor API page.

---

Pricing & Cost Calculator

Loom Transcript uses pay-per-event pricing. The repository metadata is authoritative for the build being audited; the public Store's “from” price reflects the lowest transcript tier and may lag a deployment.

Event	Current price
Actor start	$0.001 per charged start event; the 8192 MB run configuration charges eight start events
Actor usage	$0.00001 per usage unit; total depends on runtime resources
Transcript - Free	$0.38700
Transcript - Bronze	$0.37410
Transcript - Silver	$0.36120
Transcript - Gold, Platinum, Diamond	$0.34830
Translation - Free	$0.15
Translation - Bronze	$0.145
Translation - Silver	$0.14
Translation - Gold, Platinum, Diamond	$0.135

A Free-tier run with one transcript, no translation, and the fixed 8192 MB configuration starts at $0.387 + (8 × $0.001) = $0.395, plus usage events. With translation, it starts at $0.387 + $0.15 + $0.008 = $0.545, plus usage events. Failed work may still consume start and usage events; the transcript event is tied to successful Dataset publication.

Check the live pricing page before scheduling a large workload. Estimate with representative media because speech density, duration, network behavior, and translation length affect runtime.

---

Use Cases & Applications

Build a searchable recording library

Store transcript.text for whole-recording search or index timestamped segments as smaller retrieval units. Product walkthroughs, internal demonstrations, and recorded updates can then be found by spoken phrase. A downstream application can display matching text and its approximate video interval; embeddings and question answering remain downstream responsibilities.

Turn walkthroughs into working notes

Teams can turn an authorized Loom walkthrough into draft SOP steps, implementation notes, release summaries, or follow-up tasks. Segment timestamps provide a practical path back to the recording. The output is generated from audible speech, so review names, numbers, commands, and consequential instructions against the source before publishing them.

Accessibility drafts and content repurposing

The segment list can seed caption editing, show notes, summaries, articles, or social copy. It is a draft transcript, not a certified accessibility artifact. Human review remains appropriate before publication.

Review recordings across languages

Request one translation target when colleagues need to inspect the spoken content in another language. Translation preserves segment time ranges so reviewers can compare source and translated passages against the same point in the recording. Multiple target languages require separate runs and separate translation events.

Automation boundaries

This Actor is suited to a known video URL. Collect authorized Loom share URLs first, then invoke one transcription run per chosen URL. Do not treat a successful transcription as permission to republish the underlying video or transcript.

---

FAQ

Does the Actor return Loom's generated transcript?

No. The verified path downloads audible media and generates speech text independently. It does not promise Loom's existing transcript, captions, comments, or chapters.

Can it process password-protected or workspace-only videos?

No access credentials are accepted. The share URL must be publicly reachable and expose downloadable media with an audio track.

Can it process an entire Loom workspace or folder?

No. The public input accepts one video URL, and multi-video processing is disabled. Use a discovery Actor first and submit individual video URLs in separate runs.

What happens if the video has no speech?

The run fails without a transcript Dataset item. Silent clips, music-only media, missing audio, or speech that cannot be detected do not satisfy the successful output contract.

Why are some metadata fields null?

Loom or the extraction response did not expose them for that video. The schema intentionally permits nullable values instead of fabricating counts, dates, audio attribution, or author details.

Are timestamps word-accurate?

No. They are segment time ranges formatted as HH:MM:SS.mmm. They are useful for navigation and downstream processing but are not guaranteed word-level alignments.

How are long videos handled?

The Actor uses a fixed 8192 MB configuration. Media up to 3600 seconds is transcribed directly. Longer media is processed sequentially in 900-second core chunks with 15 seconds of context on each available side; only one temporary chunk is retained at a time. Runtime and cost still grow with duration and speech density, so use asynchronous runs for long inputs.

Is translation always charged when requested?

No. Translation is charged only when the complete translated structure is produced. If any segment ultimately fails, the output keeps translation empty and the translation event is not charged.

---

SEO Keywords & Search Terms

People may describe this task as converting a Loom video to text, generating a Loom transcript with timestamps, extracting spoken words from a Loom URL, or preparing video speech for search and RAG. Those phrases describe the same narrow workflow: one public video enters, and one structured transcript record leaves.

The Actor is not positioned as a Loom subtitle downloader, channel scraper, bulk transcript endpoint, audio downloader, video summarizer, or guaranteed verbatim transcription service. Keeping those boundaries explicit helps users choose the right tool and prevents misleading search claims.

For programmatic discovery, use the stable Actor name agentx/loom-transcript. For human evaluation, inspect the Input, Output, Pricing, Reviews, and Issues tabs on the live Store page.

---

Trust & Certifications

The strongest available evidence is the public contract: a schema-constrained Loom share URL, a closed 22-field Dataset schema, timestamped segments, nullable source metadata, and a complete-or-absent translation object. These properties can be inspected before integrating and validated from each completed run.

No Store rating, user count, monthly activity, bookmark total, or one-off test result is presented as evidence of future availability or transcription accuracy. Source delivery and speech recognition remain variable.

No independent accuracy certification, SLA, legal-transcript status, GDPR certification, CCPA certification, or guaranteed uptime is claimed here. Apify supplies the Actor execution and storage platform; source availability and extraction behavior remain external dependencies.

---

Legal & Compliance

Process only content you are authorized to use. Public accessibility does not remove copyright, privacy, contractual, publicity, data-protection, or platform-policy obligations. Confirm that the owner enabled appropriate link access using Loom's recording sharing guidance, and review the current Atlassian product terms for Loom and applicable law for your use case.

The Actor returns source metadata and generated speech text. It does not grant a license to the video, verify ownership, determine fair use, provide legal advice, or certify the accuracy of quotations. Avoid submitting private credentials or confidential URLs because they are not part of the supported input contract.

If a source owner deletes or restricts a video, future runs can fail even when an older run succeeded. Retain the source URL and processing time when provenance matters.

---

Related Tools

Related AgentX Actors

• YouTube Transcript handles one public YouTube video.
• TikTok Transcript handles one public TikTok video.
• Video Transcript handles uploads and supported public video URLs.

Enrich with broader discovery

• All Video Scraper provides broader video metadata and media workflows.
• All Jobs Scraper supplies cross-platform job data for content or labor-market research.
• All Shopping Scraper supplies cross-market product data for commerce research.

Choose a discovery Actor when you do not yet have a specific video URL. Keep transcription runs one video at a time.

---

Support & Community

• Actor page and documentation
• API reference
• Issues
• Telegram support

When reporting a problem, include the public video URL, run ID, expected result, observed error, and whether translation was enabled. Do not post private tokens or credentials.

Schema, code behavior, pricing metadata, public proof, the example URL, and official documentation links were last checked on July 21, 2026. Loom availability and Store statistics are volatile.

Run a one-video test · View pricing