Skip to content

List models

GET
/models

Ce point d’accès, publiquement accessible, retourne une liste de tous les modèles de transcription disponibles dans le système.

Il est possible de filtrer les résultats en utilisant des paramètres dans l’URL pour affiner la recherche.

name
string

Filtre les modèles pour trouver une correspondance exacte avec le nom fourni (ex: “large-v3”).

Example
tiny
skip
integer

The number of items to skip from the beginning of the result set. This is used for pagination, often referred to as the ‘offset’.

limit
integer

The maximum number of items to return in the response. This is used to control the page size.

Example
100

Successful response (inferred from assertions)

object
data
required
Array<object>
object
id
required

The unique numeric identifier for the model. Use this ID when creating new resources that depend on a specific model, such as a live session.

integer
Example
1
name
required

The unique, human-readable name of the transcription model (e.g., ‘tiny’, ‘large-v1’, ‘large-v2’). This name is used to select a model when creating a new live session via the API.

string
Example
tiny
active
required

Indicates whether the model is currently available for use. An inactive model (false) cannot be used to create new transcription sessions.

boolean
Example
true
vram
required

The estimated amount of VRAM (in Megabytes) required to load and run this model. This value is used to calculate resource allocation and prevent overloading the system.

integer
Example
1250
pagination
required
object
total_items
required

The total number of items available in the entire dataset that match the query, across all pages.

integer
total_pages
required

The total number of pages calculated from total_items and per_page. A client can use this to build page navigation UI.

integer
current_page
required

The page number for the current set of items being returned. This is typically controlled by skip and limit or page and size query parameters.

integer
per_page
required

The maximum number of items configured to be returned on a single page. This is typically controlled by a limit query parameter.

integer
Example
{
"data": [
{
"created_at": "2025-11-06T17:28:43.386793+01:00",
"updated_at": null,
"name": "tiny",
"active": true,
"vram": 625,
"id": 1
},
{
"created_at": "2025-11-06T17:28:43.386793+01:00",
"updated_at": null,
"name": "medium",
"active": true,
"vram": 2500,
"id": 2
},
{
"created_at": "2025-11-06T17:28:43.386793+01:00",
"updated_at": null,
"name": "large_v1",
"active": true,
"vram": 5000,
"id": 3
},
{
"created_at": "2025-11-06T17:28:43.386793+01:00",
"updated_at": null,
"name": "large_v2",
"active": true,
"vram": 5000,
"id": 4
},
{
"created_at": "2025-11-06T17:30:33.724683+01:00",
"updated_at": null,
"name": "large-v3",
"active": true,
"vram": 10000,
"id": 5
}
],
"pagination": {
"total_items": 5,
"total_pages": 1,
"current_page": 1,
"per_page": 100
}
}