Create Reframe
Create Projects
Create Reframe
Automatically reframe videos for different aspect ratios
POST
Create Reframe
For AI agents: a documentation index is at /llms.txt. Every page is also available as markdown, just append .md to the URL.
Overview
Automatically reframe videos from landscape to portrait or square formats using AI. Perfect for adapting content for TikTok, Instagram Stories, and other vertical video platforms.Rate Limiting
This endpoint is rate limited to 10 requests per minute per API key.Video Requirements
Duration
Minimum: 3 seconds
Maximum: 10 minutes
Maximum: 10 minutes
File Size
Maximum: 2 GB
Format
MP4 or MOV with valid video streams
Source Format
Works best with landscape (16:9) source videos
Plan Limits
The Automation API requires an active Studio subscription. View pricing to compare plans.
Response
string
Unique project identifier
string
Project title (usually the filename)
string
Thumbnail URL for the project
number
Duration in seconds that will be billed to your account
string
Current processing status
processing- Video is being analyzed and reframedcompleted- Reframing completed successfullyfailed- Processing failed due to an error
string
Type of project (always “reframe” for this endpoint)
string
Source of the video content (always “Upload” for this endpoint)
string
Video genre used for AI analysis
array
Array of identified topics in the video
array
Array of clip duration preferences
number
Start time in seconds for processing (null if entire video)
number
End time in seconds for processing (null if entire video)
integer
Output resolution for the reframed video
string
Output orientation for the reframed video
string
Caption style preset ID (null if captions disabled)
boolean
Whether captions are enabled
boolean
Whether emojis are added to captions
boolean
Whether keyword highlighting is enabled
string
Primary language of the video content
string
Target dubbing language (null if not applicable)
boolean
Whether transcription will be translated
array
Array of languages for translation
object
Video file metadata including duration, resolution, format, etc.
object
Project URLs and assets (populated when processing completes)
integer
Unix timestamp when the project was created
integer
Unix timestamp when the project was last updated
Example Request
Example Response
Processing Workflow
- Upload Analysis - Video is analyzed for speakers, objects, and key visual elements
- Smart Cropping - AI automatically crops and reframes to keep important content in view
- Motion Tracking - Follows speakers and maintains optimal framing throughout the video
- Segmentation - Optionally splits longer videos into optimal segments (unless disabled)
- Output Generation - Creates reframed video in the target aspect ratio
Reframing Features
- Speaker Tracking: Automatically follows speakers and keeps them centered
- Object Recognition: Identifies and tracks important visual elements
- Smart Cropping: Maintains optimal composition throughout the video
- Smooth Transitions: Ensures natural camera movements between focus points
- Auto-Segmentation: Intelligently splits content into engaging segments
Use Cases
Multi-Platform Distribution
Automatically adapt content for YouTube, TikTok, Instagram, and more
Content Management Systems
Generate all aspect ratio variants on upload for any platform
Video Hosting Platforms
Offer automatic reframing as a feature to your users
Marketing Automation
Scale ad creative production across different placements
Best Practices
- Source Quality: Use high-resolution landscape videos for best results
- Speaker Positioning: Videos with centered speakers reframe more effectively
- Content Type: Works best with talking head videos and presentations
- Duration: Shorter videos (under 5 minutes) process faster and more accurately
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Upload ID from a previously uploaded file
Video genre for better AI analysis
Available options:
talking, screenshare, gaming Target orientation
Available options:
portrait, square Whether to disable automatic splitting into segments
Response
200 - application/json
Successful response
Available options:
queued, prepped, draft, processing, finalizing, completed, invalid, expired, failed, error Available options:
clipping, captions, reframe, dubbing, transcription Available options:
Upload, Youtube, Vimeo, TwitchVod, Twitter, RumbleEmbed, Generic Available options:
talking, screenshare, gaming Available options:
landscape, portrait, square Available options:
native, roman Presigned URLs for the project's assets. URLs expire — always use the most recent API response. The transcription_* subtitle/text exports are only present on transcription projects.