Vionlabs Vertical Conversion API
Get vertical conversion data for an asset.
The response describes where the camera should focus horizontally for
every frame of the source video, expressed as x_center pixel coordinates
in the source frame's coordinate system. It also reports the
upper_black_bar / lower_black_bar positions and the source frame
dimensions.
The output is independent of any output aspect ratio. To produce a
vertical (or any other aspect-ratio) crop, the consumer chooses the crop
width around x_center and uses the black-bar positions for the crop's
top and bottom. This endpoint accepts no aspect-ratio, framing, or
cropping parameters — none are needed.
Stytch access token authentication. Requires BOTH:
- Authorization: Bearer ACCESS_TOKEN
- catalog query parameter
Example: Authorization: Bearer ACCESS_TOKEN ?catalog=my_catalog
In: header
Path Parameters
The inventory ID of the asset to get the vertical conversion for
Query Parameters
Optional vertical conversion result version to fetch. If omitted, the catalog's configured default version is used.
Response Body
application/json
application/json
curl -X GET "https://example.com/results/vertical_conversion/v1/string"{
"coordinates": [
{
"ts": 0,
"pts": 0,
"frm_idx": 0,
"x_center": 0
}
],
"upper_black_bar": 0,
"lower_black_bar": 0,
"source_frame_width": 0,
"source_frame_height": 0
}{
"detail": [
{
"loc": [
"string"
],
"msg": "string",
"type": "string"
}
]
}Get vertical conversion result status for an asset.
Stytch access token authentication. Requires BOTH:
- Authorization: Bearer ACCESS_TOKEN
- catalog query parameter
Example: Authorization: Bearer ACCESS_TOKEN ?catalog=my_catalog
In: header
Path Parameters
The inventory ID of the item to get the vertical conversion for
Query Parameters
The version of the vertical conversion to get
Response Body
application/json
application/json
curl -X GET "https://example.com/results/vertical_conversion/v1/status/string"{
"status": "success",
"error": "string",
"updated": "2019-08-24T14:15:22Z",
"version_id": "string",
"inventory_id": "string",
"type": "movie"
}{
"detail": [
{
"loc": [
"string"
],
"msg": "string",
"type": "string"
}
]
}Vionlabs Content Summary API
Vionlabs Content Summary API for summarizing information-heavy content (news segments, podcasts).
Vionlabs Recommender API
The Vionlabs Recommender API delivers content recommendations for movies and series, powered by Vionlabs' proprietary content-understanding technology. ## Endpoints The API exposes three recommendation strategies, each designed for a distinct UI placement: | Endpoint | Signal | Typical UI placement | |---|---|---| | **POST /for-you** | Full viewing history (behavioral) | Personalized "Top picks for you" row | | **POST /because-you-watched** | Single anchor item (behavioral) | "Because you watched *Title*" row | | **POST /more-like-this** | Single anchor item (content similarity) | "More like this" on a detail page | **`/for-you`** and **`/because-you-watched`** leverage aggregate viewing patterns across users — the items people watch *and the order in which they watch them* — to surface behaviorally relevant recommendations. **`/more-like-this`** is purely content-based: results depend only on the anchor item's attributes (genre, mood, narrative style, etc.) and require no user-level data.