> ## 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.
# YouTube Video Caption
> Get YouTube video caption.
**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 generate visual captions for a YouTube 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:**
Total cost = Base fee + Input tokens fee + Output tokens fee + Duration fee
* Base fee: Charged at actual cost (variable, depends on video processing requirements)
* Input tokens: \$0.45/1M tokens
* Output tokens: \$3.75/1M tokens
* Video duration: \$0.0001 per second
**Example calculation:**
For a 2-second video with 42,951 input tokens and 4,134 output tokens:
* Base: Variable (actual cost)
* Input: 42,951 × \$0.45/1M = \$0.01933
* Output: 4,134 × \$3.75/1M = \$0.01550
* Duration: 2 × \$0.0001 = \$0.0002
* **Total (excluding base): \$0.03503 + base fee**
This is an **asynchronous** endpoint. It returns a `task_id` immediately. You must configure a [Webhook](/visual-intelligence/getting-started/webhooks) to receive the processing results.
If no webhook is configured on the account, the call is **rejected at submit time** with `HTTP 400` and:
```json theme={null}
{"code": 400, "msg": "An async request requires at least one webhook.", "data": null}
```
(No `success` / `failed` flags on this error path.)
### 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 youtube_video_caption(video_url: str):
url = f"{BASE_URL}/youtube/video/mai/transcript"
data = {"video_url": video_url}
resp = requests.post(url, headers=HEADERS, json=data)
return resp.json()
# Usage example
result = youtube_video_caption("https://www.youtube.com/shorts/m8sOA8MxmQE")
print(result)
```
### Response
Returns the caption task information.
```json Response theme={null}
{
"code": 200,
"msg": "success",
"data": {
"task_id": "1cd78354af824c8eb1dafe4ed2435720"
},
"failed": false,
"success": true
}
```
```json Callback Response theme={null}
{
"code": 200,
"message": "SUCCESS",
"data": {
"videoTranscript": {
"data": {
"data": [
{
"end_time": 2.0,
"start_time": 0.0,
"transcript": "A young woman with dark hair and a black tank top leans against a tree, looking off to the side with a pensive expression. The video has a greenish overlay and text overlays reading \"When you realize your real dad\" and \"is not who you thought he was\" with a Snap Original logo."
},
{
"end_time": 4.0,
"start_time": 2.0,
"transcript": "The woman continues to look off to the side, her expression unchanged."
},
{
"end_time": 6.0,
"start_time": 4.0,
"transcript": "The scene remains largely the same, with the woman still looking off to the side."
}
],
"error_rate": 0.0,
"usage_metadata": {
"duration": 0.0,
"model": "openai/gpt-5-mini",
"output_tokens": 4134,
"prompt_tokens": 42951
}
},
"msg": "Video transcription completed successfully",
"success": true
},
"audioTranscript": {
"data": {
"data": [
{
"end_time": 2.0,
"speaker": null,
"start_time": 0.0,
"text": " Oh"
}
],
"usage_metadata": {
"duration": 2,
"model": "whisper-1",
"output_tokens": 0,
"prompt_tokens": 0
}
},
"msg": "ASR transcription completed successfully",
"success": true
}
},
"task_id": "4330ce434e744cdb8e325c96a20e1460"
}
```
### Response Parameters
| Parameter | Type | Description |
| ------------- | ------- | ------------------------------------------------ |
| code | string | Response code indicating the result status |
| msg | string | Response message describing the operation result |
| data | object | Response data object containing task information |
| data.task\_id | string | Unique identifier of the caption task |
| success | boolean | Indicates whether the operation was successful |
| failed | boolean | Indicates whether the operation failed |
### Callback Response Parameters
When the YouTube video caption generation is complete, a callback will be sent to your configured webhook URL.
| Parameter | Type | Description |
| -------------------------------------------------------- | -------------- | ------------------------------------------------------------------------------- |
| code | string | Response code (200 indicates success) |
| message | string | Status message (e.g., "SUCCESS") |
| data | object | Response data object containing both video and audio transcription results |
| data.videoTranscript | object | Video transcription result object |
| data.videoTranscript.data | object | Inner data object containing video caption segments and usage information |
| data.videoTranscript.data.data | array | Array of video caption segments with timestamps |
| data.videoTranscript.data.data\[].start\_time | number | Start time of the video segment in seconds |
| data.videoTranscript.data.data\[].end\_time | number | End time of the video segment in seconds |
| data.videoTranscript.data.data\[].transcript | string | Video transcription text describing the visual content |
| data.videoTranscript.data.error\_rate | number | Error rate of the video caption (0.0 means no errors) |
| data.videoTranscript.data.usage\_metadata | object | Usage statistics for the video caption |
| data.videoTranscript.data.usage\_metadata.duration | number | Processing duration in seconds |
| data.videoTranscript.data.usage\_metadata.model | string | The AI model used for video caption (e.g., "openai/gpt-5-mini") |
| data.videoTranscript.data.usage\_metadata.output\_tokens | integer | Number of tokens in the generated video caption |
| data.videoTranscript.data.usage\_metadata.prompt\_tokens | integer | Number of tokens in the input prompt |
| data.videoTranscript.msg | string | Detailed message about the video caption result |
| data.videoTranscript.success | boolean | Indicates whether the video caption was successful |
| data.audioTranscript | object | Audio transcription result object |
| data.audioTranscript.data | object | Inner data object containing audio transcription segments and usage information |
| data.audioTranscript.data.data | array | Array of audio transcription segments with timestamps |
| data.audioTranscript.data.data\[].start\_time | number | Start time of the audio segment in seconds |
| data.audioTranscript.data.data\[].end\_time | number | End time of the audio segment in seconds |
| data.audioTranscript.data.data\[].text | string | Audio transcription text for this segment |
| data.audioTranscript.data.data\[].speaker | string \| null | Speaker identifier (null if speaker identification not enabled) |
| data.audioTranscript.data.usage\_metadata | object | Usage statistics for the audio transcription |
| data.audioTranscript.data.usage\_metadata.duration | number | Audio duration in seconds |
| data.audioTranscript.data.usage\_metadata.model | string | The model used for audio transcription (e.g., "whisper-1") |
| data.audioTranscript.data.usage\_metadata.output\_tokens | integer | Number of output tokens (0 for audio transcription) |
| data.audioTranscript.data.usage\_metadata.prompt\_tokens | integer | Number of prompt tokens (0 for audio transcription) |
| data.audioTranscript.msg | string | Detailed message about the audio transcription result |
| data.audioTranscript.success | boolean | Indicates whether the audio transcription was successful |
| task\_id | string | The task ID associated with this transcription request |
## OpenAPI
````yaml POST /youtube/video/mai/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:
/youtube/video/mai/transcript:
post:
summary: YouTube Video Caption
description: Get YouTube video caption.
operationId: youtube_video_mai_transcript
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
video_url:
type: string
description: The YouTube video URL
example: https://www.youtube.com/shorts/m8sOA8MxmQE
required:
- video_url
responses:
'200':
description: Transcription task information
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: object
properties:
task_id:
type: string
example: 1cd78354af824c8eb1dafe4ed2435720
description: Unique identifier of the transcription task
description: Response data object containing task information
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
````