> ## Documentation Index
> Fetch the complete documentation index at: https://api-tools.memories.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Twitter Video Transcript
> Get Twitter video transcript.
**Product**: Visual Intelligence — Social Media Scraping
**Use case**: Fetch video metadata, transcripts, captions, and comments from YouTube, Instagram, TikTok, and Twitter/X
**Host**: `https://mavi-backend.memories.ai/serve/api/v2`
**Auth**: `Authorization: sk-mavi-...` (no `Bearer` prefix)
This endpoint allows you to retrieve transcript for a Twitter video.
Channel routing guide: see [Social Media Scraping Overview](/visual-intelligence/social-media-scraping-overview). Endpoints with a `channel` request field let you choose `apify`, `rapid`, or `memories.ai`; endpoints without this field use managed routing.
**Pricing:**
* **rapid** channel: \$0.01 per video
* **memories.ai** channel: \$0.01 per video
* **apify** channel: Charged at Apify's actual cost (higher and variable pricing)
### Code Example
```python Python theme={null}
import requests
BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2"
API_KEY = "sk-mavi-..."
HEADERS = {
"Authorization": f"{API_KEY}"
}
def twitter_video_transcript(video_url: str, channel: str):
url = f"{BASE_URL}/twitter/video/transcript"
data = {"video_url": video_url, "channel": channel}
resp = requests.post(url, headers=HEADERS, json=data)
return resp.json()
# Usage example
result = twitter_video_transcript("https://x.com/NBCOlympics/status/1989901761650323606", "apify")
print(result)
```
### Request Body
| Field | Type | Required | Description |
| ---------- | ------ | -------- | ------------------------------------------------------------------- |
| video\_url | string | Yes | The Twitter video URL |
| channel | string | Yes | The channel name. Supported values: `apify`, `rapid`, `memories.ai` |
### Response
**Response shape depends on the `channel` parameter** — same channel-dependent split as the other scraping endpoints. Verified live:
* `channel: "apify"` — `data` is an **array** with one object: `{ transcript }` (matches the example below).
* `channel: "memories.ai"` — `data` is an **object**: `{ success, transcript }`.
* `channel: "rapid"` — same alternative shape as `memories.ai`.
```json theme={null}
{
"code": 200,
"msg": "success",
"data": [
{
"tweetId": "1989901761650323606",
"transcript_text": ">> 159.97 SO HE GOES. INTO THE LEAD AND THIS PLAY. LEAD AND THIS PLAY. >> HIS REACTION. >> HIS REACTION. >> YES. >> YES. >> FIRST PLACE ARE.",
"json_text": [],
"webvtt_text": "WEBVTT\n\n00:00:00.000 --> 00:00:05.696\n>> 159.97 SO HE GOES. INTO THE \nLEAD AND THIS PLAY.\n\n00:00:05.707 --> 00:00:07.974\nLEAD AND THIS PLAY. \n>> HIS REACTION.\n\n00:00:07.975 --> 00:00:08.208\n>> HIS REACTION. \n>> YES.\n\n00:00:08.242 --> 00:00:18.218\n>> YES. \n>> FIRST PLACE ARE.\n"
}
],
"failed": false,
"success": true
}
```
### Response Parameters
| Parameter | Type | Description |
| ------------------------ | -------------- | --------------------------------------------------- |
| code | string | Response code indicating the result status |
| msg | string | Response message describing the operation result |
| data | array\[object] | Array containing transcript data objects |
| data\[].tweetId | string | Twitter/X tweet ID |
| data\[].transcript\_text | string | Plain text transcript without timing information |
| data\[].json\_text | array | JSON format transcript (may be empty array) |
| data\[].webvtt\_text | string | Transcript in WEBVTT format with timing information |
| success | boolean | Indicates whether the operation was successful |
| failed | boolean | Indicates whether the operation failed |
## OpenAPI
````yaml POST /twitter/video/transcript
openapi: 3.1.0
info:
title: Video Metadata & Transcript API Reference
description: >-
REST APIs for retrieving video metadata and transcripts from YouTube,
Instagram, TikTok, and Twitter
version: v1.0.1
servers:
- url: https://mavi-backend.memories.ai/serve/api/v2
security:
- ApiKeyAuth: []
paths:
/twitter/video/transcript:
post:
summary: Twitter Video Transcript
description: Get Twitter video transcript.
operationId: twitter_video_transcript
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
video_url:
type: string
description: The Twitter video URL
example: https://x.com/NBCOlympics/status/1989901761650323606
channel:
type: string
description: >-
The channel name. Supported values: apify, rapid,
memories.ai
enum:
- apify
- rapid
- memories.ai
example: apify
required:
- video_url
- channel
responses:
'200':
description: Video transcript in multiple formats (plain text and WEBVTT)
content:
application/json:
schema:
type: object
properties:
code:
type: string
example: 200
description: Response code indicating the result status
msg:
type: string
example: success
description: Response message describing the operation result
data:
type: array
items:
type: object
properties:
tweetId:
type: string
example: '1989901761650323606'
description: Twitter/X tweet ID
transcript_text:
type: string
example: >-
>> 159.97 SO HE GOES. INTO THE LEAD AND THIS PLAY.
LEAD AND THIS PLAY. >> HIS REACTION. >> HIS
REACTION. >> YES. >> YES. >> FIRST PLACE ARE.
description: Plain text transcript without timing information
json_text:
type: array
items:
type: object
example: []
description: JSON format transcript (may be empty array)
webvtt_text:
type: string
example: |-
WEBVTT
00:00:00.000 --> 00:00:05.696
>> 159.97 SO HE GOES. INTO THE
LEAD AND THIS PLAY.
00:00:05.707 --> 00:00:07.974
LEAD AND THIS PLAY.
>> HIS REACTION.
description: Transcript in WEBVTT format with timing information
description: Array containing transcript data objects
success:
type: boolean
example: true
description: Indicates whether the operation was successful
failed:
type: boolean
example: false
description: Indicates whether the operation failed
components:
securitySchemes:
ApiKeyAuth:
type: apiKey
in: header
name: Authorization
````