You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* This file was auto-generated by Fern from our API Definition.
3
+
*/
4
+
5
+
import*asHumefrom"..";
6
+
7
+
exportinterfaceModelsInput{
8
+
data?: string;
9
+
/**
10
+
* Configuration used to specify which models should be used and with what settings.
11
+
*
12
+
*/
13
+
models?: Hume.ModelsInputModels;
14
+
/**
15
+
* Length in milliseconds of streaming sliding window.
16
+
*
17
+
* Extending the length of this window will prepend media context from past payloads into the current payload.
18
+
*
19
+
* For example, if on the first payload you send 500ms of data and on the second payload you send an additional 500ms of data, a window of at least 1000ms will allow the model to process all 1000ms of stream data.
20
+
*
21
+
* A window of 600ms would append the full 500ms of the second payload to the last 100ms of the first payload.
22
+
*
23
+
* Note: This feature is currently only supported for audio data and audio models. For other file types and models this parameter will be ignored.
24
+
*
25
+
*/
26
+
streamWindowMs?: number;
27
+
/**
28
+
* Whether to reset the streaming sliding window before processing the current payload.
29
+
*
30
+
* If this parameter is set to `true` then past context will be deleted before processing the current payload.
31
+
*
32
+
* Use reset_stream when one audio file is done being processed and you do not want context to leak across files.
33
+
*
34
+
*/
35
+
resetStream?: boolean;
36
+
/**
37
+
* Set to `true` to enable the data parameter to be parsed as raw text rather than base64 encoded bytes.
38
+
* This parameter is useful if you want to send text to be processed by the language model, but it cannot be used with other file types like audio, image, or video.
39
+
*
40
+
*/
41
+
rawText?: boolean;
42
+
/**
43
+
* Set to `true` to get details about the job.
44
+
*
45
+
* This parameter can be set in the same payload as data or it can be set without data and models configuration to get the job details between payloads.
46
+
*
47
+
* This parameter is useful to get the unique job ID.
48
+
*
49
+
*/
50
+
jobDetails?: boolean;
51
+
/**
52
+
* Pass an arbitrary string as the payload ID and get it back at the top level of the socket response.
53
+
*
54
+
* This can be useful if you have multiple requests running asynchronously and want to disambiguate responses as they are received.
* This file was auto-generated by Fern from our API Definition.
3
+
*/
4
+
5
+
import*asHumefrom"..";
6
+
7
+
/**
8
+
* Configuration used to specify which models should be used and with what settings.
9
+
*
10
+
*/
11
+
exportinterfaceModelsInputModels{
12
+
/**
13
+
* Configuration for the vocal burst emotion model.
14
+
*
15
+
* Note: Model configuration is not currently available in streaming.
16
+
*
17
+
* Please use the default configuration by passing an empty object `{}`.
18
+
*
19
+
*/
20
+
burst?: Record<string,unknown>;
21
+
/**
22
+
* Configuration for the facial expression emotion model.
23
+
*
24
+
* Note: Using the `reset_stream` parameter does not have any effect on face identification. A single face identifier cache is maintained over a full session whether `reset_stream` is used or not.
25
+
*
26
+
*/
27
+
face?: Hume.ModelsInputModelsFace;
28
+
/**
29
+
* Configuration for the facemesh emotion model.
30
+
*
31
+
* Note: Model configuration is not currently available in streaming.
32
+
*
33
+
* Please use the default configuration by passing an empty object `{}`.
34
+
*
35
+
*/
36
+
facemesh?: Record<string,unknown>;
37
+
/** Configuration for the language emotion model. */
38
+
language?: Hume.ModelsInputModelsLanguage;
39
+
/**
40
+
* Configuration for the speech prosody emotion model.
41
+
*
42
+
* Note: Model configuration is not currently available in streaming.
43
+
*
44
+
* Please use the default configuration by passing an empty object `{}`.
* This file was auto-generated by Fern from our API Definition.
3
+
*/
4
+
5
+
/**
6
+
* Configuration for the facial expression emotion model.
7
+
*
8
+
* Note: Using the `reset_stream` parameter does not have any effect on face identification. A single face identifier cache is maintained over a full session whether `reset_stream` is used or not.
9
+
*
10
+
*/
11
+
exportinterfaceModelsInputModelsFace{
12
+
/** Configuration for FACS predictions. If missing or null, no FACS predictions will be generated. */
13
+
facs?: Record<string,unknown>;
14
+
/** Configuration for Descriptions predictions. If missing or null, no Descriptions predictions will be generated. */
15
+
descriptions?: Record<string,unknown>;
16
+
/**
17
+
* Whether to return identifiers for faces across frames. If true, unique identifiers will be assigned to face bounding boxes to differentiate different faces. If false, all faces will be tagged with an "unknown" ID.
18
+
*
19
+
*/
20
+
identifyFaces?: boolean;
21
+
/**
22
+
* Number of frames per second to process. Other frames will be omitted from the response.
23
+
*
24
+
*/
25
+
fpsPred?: number;
26
+
/**
27
+
* Face detection probability threshold. Faces detected with a probability less than this threshold will be omitted from the response.
28
+
*
29
+
*/
30
+
probThreshold?: number;
31
+
/**
32
+
* Minimum bounding box side length in pixels to treat as a face. Faces detected with a bounding box side length in pixels less than this threshold will be omitted from the response.
* This file was auto-generated by Fern from our API Definition.
3
+
*/
4
+
5
+
/**
6
+
* Configuration for the language emotion model.
7
+
*/
8
+
exportinterfaceModelsInputModelsLanguage{
9
+
/** Configuration for sentiment predictions. If missing or null, no sentiment predictions will be generated. */
10
+
sentiment?: Record<string,unknown>;
11
+
/** Configuration for toxicity predictions. If missing or null, no toxicity predictions will be generated. */
12
+
toxicity?: Record<string,unknown>;
13
+
/** The granularity at which to generate predictions. Values are `word`, `sentence`, `utterance`, or `passage`. To get a single prediction for the entire text of your streaming payload use `passage`. Default value is `word`. */
![fern-api[bot]](https://avatars.githubusercontent.com/in/244756?v=4&size=40){kind=avatar}
0 commit comments