Facebook Transcript - Timestamped Facebook Speech-to-Text API

Facebook Transcript converts one public Facebook 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 Facebook caption tracks or existing subtitle files.

• Submit one specific public Facebook video or Reel URL; Pages, profiles, groups, feeds, and URL lists are outside the input contract.
• Redirects are resolved silently and the extractor must identify Facebook before the formal media download begins.
• A successful run publishes one 22-field Dataset item joining available post context to detected speech intervals.
• Private, friends-only, group-restricted, login-gated, or removed media is not supported through hidden credentials.

Run Facebook Transcript · Open the API page

Start with a video that plays publicly in a signed-out browser and contains clear dialogue. Check names, post metadata, and translation before scheduling repeated runs.

---

Why Choose This API

A narrow contract for one known Facebook video

This Actor serves workflows that already have an exact Facebook media permalink and need the spoken words. It accepts one URL and one optional target language. Redirect resolution handles common share links, while extractor identity provides the final platform decision.

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

Capability	What is returned
Generated speech	Detected language, joined transcript, and ordered start / end / text ranges
Facebook source	Post title/description, Page or profile identifiers, duration, publish time, thumbnail, categories, and tags when exposed
Available engagement	Views, reactions/likes, shares, comments, and other supported nullable counters
Optional language layer	One complete translation retaining the source segment order and timing

It does not crawl a Page, enumerate a profile, monitor a feed, enter a private group, capture Live video, export Facebook captions, identify speakers, summarize content, or deliver the video file. Missing source values remain explicitly empty under the schema.

ASR works from the accessible audio track. Low-volume speech, background music, multiple speakers, accents, compression, and names can affect accuracy. Verify high-impact quotations against the public player.

---

Quick Start Guide

Run in Apify Console

1. Open Facebook Transcript on Apify.
2. While signed out, confirm the desired video or Reel plays, then copy its permalink into Video URL.
3. Leave Translate empty for source speech, or select one target language.
4. Start the Actor and inspect its single Dataset item after completion.

The input schema currently pre-fills this public video permalink:

{
  "video_url": "https://www.facebook.com/61560499803610/videos/866929398761397/",
  "translate": "spanish"
}

The guide reuses the same permalink in API and response examples. That does not make it permanent: the owner or Facebook can delete it, change audience settings, add a login gate, or restrict a region. Replace an inaccessible source with another publicly playable video.

What success means

The result is successful only after media with audio is prepared, speech is detected, and one normalized record is published. A post title or HTML response without transcript segments is insufficient.

---

Input Parameters

Input configuration

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

Each run handles one media permalink. Page and profile roots, feeds, searches, group-only content, private posts, uploads, cookies, credentials, and URL arrays are excluded; playlist-style expansion is disabled.

Facebook URL shape alone is not enough. The resolved page must remain accessible without supplied credentials and expose a playable audio track. Deletion, audience changes, regional controls, login challenges, or extractor changes can still fail.

Translation starts from the completed source segments. Workers may translate in parallel, then rebuild source order. Any final segment failure suppresses the entire optional structure and its charge instead of returning partial or copied source text.

---

Output Data Schema

One 22-field Dataset item

One successfully transcribed post creates one 22-key Dataset object:

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 same video-and-Spanish input:

{
  "processor": "https://apify.com/agentx/facebook-transcript?fpr=aiagentapi",
  "processed_at": "2026-07-21T13:30:00+00:00",
  "platform": "Facebook",
  "title": "JUST AN INCHIDENT - F1 meme origin story",
  "author": "CadenceBraking - F1 + Motorsport",
    "duration": 50,
  "view_count": 7157,
    "categories": [],
  "tags": [],
  "transcript": {
    "language": "English",
    "text": "The origin story of F1's just an incident meme.",
    "segments": [
      {
        "start": "00:00:00.190",
        "end": "00:00:10.099",
        "text": "The origin story of F1's just an incident meme."
      }
    ]
  },
  "translation": {
    "language": "Spanish",
    "text": "El origen del meme de Fórmula 1 sobre solo un incidente.",
    "segments": [
      {
        "start": "00:00:00.190",
        "end": "00:00:10.099",
        "text": "El origen del meme de Fórmula 1 sobre solo un incidente."
      }
    ]
  }
}

Example counters and source strings are snapshots. The Actor does not append the video file, Facebook captions, SRT/VTT, OCR text, speaker identities, word-level timing, confidence, a summary, or a legal conclusion.

---

Integration Examples

REST API

The synchronous endpoint returns Dataset items directly:

curl -L "https://api.apify.com/v2/actors/agentx~facebook-transcript/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://www.facebook.com/61560499803610/videos/866929398761397/",
    "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/facebook-transcript").call(
    run_input={
        "video_url": "https://www.facebook.com/61560499803610/videos/866929398761397/",
        "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/facebook-transcript",
      "headers": {
        "Authorization": "Bearer YOUR_APIFY_TOKEN"
      }
    }
  }
}

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

---

Pricing & Cost Calculator

Facebook Transcript uses pay-per-event billing. The local metadata below is authoritative for this build; a public Store page represents the last deployment and may remain older.

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	$0.35100
Transcript - Bronze	$0.33930
Transcript - Silver	$0.32760
Transcript - Gold, Platinum, Diamond	$0.31590
Translation - Free	$0.13000
Translation - Bronze	$0.12567
Translation - Silver	$0.12133
Translation - Gold, Platinum, Diamond	$0.11700

At Free tier, one transcript on the fixed 8192 MB allocation has a fixed subtotal of $0.351 + (8 × $0.001) = $0.359, plus usage. A complete translation changes that subtotal to $0.351 + $0.13 + $0.008 = $0.489. Start and runtime usage can accrue before a later failure.

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

Search and retrieval over one video

Use the full text for post-level retrieval or index segments so search results can point back to an approximate interval. Embeddings and question answering belong to the consumer.

Editorial and research review

Journalists, community teams, researchers, and moderators can review speech alongside Page/profile context, publish time, and available counters. Preserve the permalink and manually verify consequential quotations.

Accessibility drafts and content repurposing

Segment intervals can support caption drafts, internal review, articles, summaries, or localized copy. They are not Facebook caption exports or certified accessibility assets.

Multilingual review

Select one target to compare source and translated segments on the same time windows. Each additional language requires a separate run and successful translation event.

Automation boundaries

Use an authorized Page or discovery flow to obtain candidate permalinks, then submit selected videos individually. Technical access is not permission to republish media or generated text.

---

FAQ

Does the Actor return Facebook captions or on-screen text?

No. The code prepares audio and generates speech text. It does not promise Facebook's caption track or recognition of text rendered inside the frames.

Can it process Facebook Reels?

A public Reel can work when its URL resolves to downloadable media with an audio track. Test the exact URL; private, removed, restricted, story, and live content is not promised.

Can it process an entire Page or profile?

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?

Facebook 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 runtime has 8192 MB and 2 CPUs. Above 3600 seconds, it uses sequential 900-second core blocks with 15-second boundary context, then merges owned ranges. Longer Facebook videos still increase wall time and CU.

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

Facebook video to text, transcribe a Facebook Reel, timestamped Facebook speech, and Facebook video transcript for RAG all describe this one-permalink workflow.

It is not a caption downloader, Page/profile scraper, feed crawler, private-group reader, bulk endpoint, media downloader, summarizer, OCR tool, or guaranteed-verbatim service.

Use agentx/facebook-transcript for API discovery. After publishing, check live Input, Output, Pricing, Reviews, and Issues rather than assuming the older online snapshot matches local files.

---

Trust & Certifications

Local evidence establishes the bounded interface: two closed input fields, 22 Dataset/view/display keys, Facebook extractor confirmation, nullable source values, and all-or-nothing translation. It cannot establish lasting access to an externally controlled post.

Ratings, users, monthly activity, and bookmarks are omitted because publication state and host metrics change independently of the repository.

No independent ASR accuracy certificate, SLA, legal-transcript designation, privacy certification, or uptime guarantee is claimed. Facebook controls source access and generated speech still requires review.

---

Legal & Compliance

Process only content you are authorized to use. Public accessibility does not remove copyright, privacy, contractual, publicity, or data-protection duties. Meta's Terms of Service prohibit automated collection without prior permission, and the separate Automated Data Collection Terms require express written authorization. Confirm authorization before using this Actor.

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

• TikTok Transcript handles one public TikTok video.
• YouTube Transcript handles one public YouTube video.
• Video Transcript accepts uploaded media and many supported public platforms.

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.

The local schemas, implemented behavior, pricing metadata, and cited Meta terms were reviewed on July 21, 2026. Example availability and Store statistics remain volatile.

Run a one-video test · View pricing