# Facebook Video Transcript · Reels, Watch · AI, no API key (`blue59/facebook-transcript-ai`) Actor

Transcripts for Facebook videos, Reels and Watch links. Uses Facebook's captions when they exist and built-in Whisper AI when they don't — no API key needed, no login. Any language. Quality-gated: empty or garbage results are never returned or charged.

- **URL**: https://apify.com/blue59/facebook-transcript-ai.md
- **Developed by:** [Blue59](https://apify.com/blue59) (community)
- **Categories:**
- **Stats:** 2 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $5.00 / 1,000 caption transcript (per video)s

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Facebook Video Transcript Scraper · videos, Reels, Watch

**Paste public Facebook video, Reel or Watch links — get the full spoken text.** No API key, no login.

Facebook videos sometimes carry captions; most Reels don't. This Actor uses Facebook's captions when they exist (fast, cheap) and transcribes the audio with Whisper large-v3-turbo when they don't — so you get text for every spoken-word video, not just the captioned ones. Every result passes a quality gate: empty, truncated or garbage transcripts are reported as failures and **never charged**.

### Supported links

| Link type | Example |
|---|---|
| Watch | `https://www.facebook.com/watch/?v=10153231379946729` |
| Page video | `https://www.facebook.com/<page>/videos/<id>/` |
| Reel | `https://www.facebook.com/reel/<id>` |
| Short link | `https://fb.watch/<code>/` |

Only publicly viewable videos work (private groups / login-only content are skipped and not charged).

### Output

```json
{
  "platform": "facebook",
  "id": "10153231379946729",
  "url": "https://www.facebook.com/watch/?v=10153231379946729",
  "title": "How to Share With Just Friends",
  "author": "Facebook",
  "duration": 91,
  "language": "auto",
  "source": "ai:groq-whisper-turbo",
  "charCount": 667,
  "aiMinutes": 2,
  "transcript": "..."
}
```

`source` tells you where the text came from: `caption:manual`, `caption:auto` or `ai:groq-whisper-turbo`.

### Pricing (pay per event)

- **Caption transcript** — charged when Facebook already has captions.
- **AI transcript** + **AI minute** — charged only when AI transcription succeeds; minutes are counted per started minute of audio.
- **Bring your own Groq key** (optional) — pay only the small per-result fee, no per-minute charge. Free keys at [console.groq.com](https://console.groq.com).

Set **Max minutes per video** to cap cost on long videos (default 60).

### Input

| Field | Description |
|---|---|
| `videoUrls` | Facebook video / Reel / Watch links (other platforms also accepted) |
| `aiTranscription` | Use AI when no captions (default on) |
| `languageHint` | Spoken language code (e.g. `en`, `zh`, `ja`) — improves accuracy on short clips |
| `maxMinutes` | Skip AI for videos longer than this |
| `groqApiKey` | Optional: your own key (cheaper) |
| `preferredLanguages` | Caption track priority |

### Who uses this

- Page & competitor content research: turn videos and Reels into searchable text
- Feeding RAG, summarization and LLM pipelines with clean transcripts
- Subtitling, translation, accessibility
- Social listening and ad-creative analysis

### Notes

Facebook sometimes blocks datacenter IPs — keep Apify Proxy enabled (default). Failures are classified (proxy / rate-limit / blocked / network / other) in the run report so you can see *why* something failed, not just that it did.

# Actor input Schema

## `videoUrls` (type: `array`):

One per line: facebook.com/watch/?v=…, facebook.com/<page>/videos/…, facebook.com/reel/…, fb.watch/… — must be publicly viewable (no login is used). Other platforms (TikTok, YouTube, X…) also work but are not this Actor's focus.

## `aiTranscription` (type: `boolean`):

Facebook captions are used first when the video has them. Otherwise built-in Whisper (large-v3-turbo) transcribes the audio — charged per video + per audio minute. Turn off to use captions only (videos without captions are then skipped, not charged).

## `languageHint` (type: `string`):

ISO code of the spoken language, e.g. en, zh, ja, es. Leave empty for auto-detect. Only used on the AI path.

## `maxMinutes` (type: `integer`):

Videos longer than this are skipped for AI transcription (cost guard). Caption path is not limited.

## `groqApiKey` (type: `string`):

Bring your own key from console.groq.com and pay only a small per-result fee on the AI path (no per-minute charge). Used for this run only, never stored.

## `preferredLanguages` (type: `array`):

Which caption track to prefer when several exist.

## `maxItems` (type: `integer`):

Upper limit per run.

## `minChars` (type: `integer`):

Results shorter than this are treated as failures (not charged).

## `proxyConfiguration` (type: `object`):

Apify Proxy is recommended; Facebook sometimes blocks datacenter IPs.

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.facebook.com/watch/?v=10153231379946729"
  ],
  "aiTranscription": true,
  "maxMinutes": 60,
  "preferredLanguages": [
    "en",
    "zh-Hant",
    "zh-TW",
    "zh-Hans",
    "zh",
    "ja",
    "ko",
    "es",
    "fr",
    "de",
    "pt"
  ],
  "maxItems": 100,
  "minChars": 20,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

# Actor output Schema

## `transcripts` (type: `string`):

所有結果(JSON)/ All results as JSON

## `transcriptsCsv` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "videoUrls": [
        "https://www.facebook.com/watch/?v=10153231379946729"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("blue59/facebook-transcript-ai").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "videoUrls": ["https://www.facebook.com/watch/?v=10153231379946729"] }

# Run the Actor and wait for it to finish
run = client.actor("blue59/facebook-transcript-ai").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "videoUrls": [
    "https://www.facebook.com/watch/?v=10153231379946729"
  ]
}' |
apify call blue59/facebook-transcript-ai --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,blue59/facebook-transcript-ai"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/ZNYfmmJwoWWuCBRcB/builds/mvD0fObTl7pUblCO5/openapi.json