List jobs

The maximum number of jobs to include in the response.

Start inference job

Get the request details and state of a given job.

Embedding Generation

Inference

Get job details

Get the JSON predictions of a completed measurement or custom models inference job.

Get job predictions

Get the artifacts ZIP of a completed measurement or custom models inference job.

Get job artifacts

Start inference job from local file

Batch

Stream

Alternative

Bcp47Tag

BoundingBox

x-coordinate of bounding box top left corner.

y-coordinate of bounding box top left corner.

BurstPrediction

A high-dimensional embedding in emotion space.

Modality-specific descriptive features and their scores.

Classification

CompletedEmbeddingGeneration

When this job was created (Unix timestamp in milliseconds).

When this job started (Unix timestamp in milliseconds).

When this job ended (Unix timestamp in milliseconds).

CompletedInference

The number of predictions that were generated by this job.

The number of errors that occurred while running this job.

CompletedTlInference

CompletedTraining

CustomModel

CustomModelId

CustomModelPrediction

CustomModelRequest

CustomModelVersionId

Dataset

DatasetId

DatasetVersionId

DescriptionsScore

Name of the descriptive feature being expressed.

Embedding value for the descriptive feature being expressed.

Direction

EmbeddingGenerationBaseRequest

File ID and File URL pairs for an asset registry file

EmotionEmbedding

EmotionEmbeddingItem

Embedding value for the emotion being expressed.

EmotionScore

Error

A file path relative to the top level source URL or file.

EvaluationArgs

Face

Face detection probability threshold. Faces detected with a probability less than this threshold will be omitted from the response.

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.

Whether to extract and save the detected faces in the artifacts zip created by each job.

FacePrediction

Time in seconds when face detection occurred.

The predicted probability that a detected face was actually a face.

FacemeshPrediction

FacsScore

Name of the FACS 2.0 feature being expressed.

Embedding value for the FACS 2.0 feature being expressed.

Failed

File

Granularity

GroupedPredictionsBurstPrediction

GroupedPredictionsFacePrediction

GroupedPredictionsFacemeshPrediction

GroupedPredictionsLanguagePrediction

GroupedPredictionsNerPrediction

GroupedPredictionsProsodyPrediction

InProgress

InferenceBaseRequest

List of File IDs corresponding to the files in the asset registry.

Text to supply directly to our language and NER models.

Whether to send an email notification to the user upon job completion/failure.

InferencePrediction

InferenceRequest

InferenceResults

InferenceSourcePredictResult

JobEmbeddingGeneration

JobId

JobInference

JobTlInference

JobTraining

Language

LanguagePrediction

A segment of text (like a word or a sentence).

Models

ModelsPredictions

NerPrediction

Our NER model's relative confidence in the recognized topic or entity.

A measure of how often the entity is linked to by other entities.

A URL which provides more information about the recognized topic or entity.

The specific word to which the emotion predictions are linked.

Null

Position of a segment of text within a larger document, measured in characters. Uses zero-based indexing. The beginning index is inclusive and the end index is exclusive.

PositionInterval

The index of the first character in the text segment, inclusive.

The index of the last character in the text segment, exclusive.

PredictionsOptionalNullBurstPrediction

PredictionsOptionalNullFacePrediction

PredictionsOptionalNullFacemeshPrediction

PredictionsOptionalTranscriptionMetadataLanguagePrediction

PredictionsOptionalTranscriptionMetadataNerPrediction

PredictionsOptionalTranscriptionMetadataProsodyPrediction

Prosody

ProsodyPrediction

Queued

RegistryFileDetail

Regression

Sentiment

SentimentItem

Level of sentiment, ranging from 1 (negative) to 9 (positive)

SentimentScore

SortBy

Source

SourceFile

SourceTextSource

SourceUrl

StateEmbeddingGeneration

StateEmbeddingGenerationCompletedEmbeddingGeneration

StateEmbeddingGenerationFailed

StateEmbeddingGenerationInProgress

StateEmbeddingGenerationQueued

StateInference

StateInferenceCompletedInference

StateInferenceFailed

StateInferenceInProgress

StateInferenceQueued

StateTlInference

StateTlInferenceCompletedTlInference

StateTlInferenceFailed

StateTlInferenceInProgress

StateTlInferenceQueued

StateTraining

StateTrainingCompletedTraining

StateTrainingFailed

StateTrainingInProgress

StateTrainingQueued

Status

Target

Task

TaskClassification

TaskRegression

TextPosition

TextSource

A time range with a beginning and end, measured in seconds.

TimeInterval

TimeRange

TlInferenceBaseRequest

TlInferencePrediction

TlInferenceResults

TlInferenceSourcePredictResult

Toxicity

ToxicityItem

ToxicityScore

TrainingBaseRequest

TrainingCustomModel

Transcription

Transcript confidence threshold. Transcripts generated with a confidence less than this threshold will be considered invalid and not used as an input for model inference.

Transcription metadata for your media file.

TranscriptionMetadata

Type

Unconfigurable

UnionJob

UnionJobJobEmbeddingGeneration

UnionJobJobInference

UnionJobJobTlInference

UnionJobJobTraining

UnionPredictResult

ValidationArgs

When

Window

StreamBurst

If a payload ID was passed in the request, the same payload ID will be sent back in the response body.

Response for the vocal burst emotion model.

Response for the facial expression emotion model.

Response for the speech prosody emotion model.

StreamBurstBurst

StreamBurstBurstPredictionsItem

StreamBurstFace

StreamBurstFacePredictionsItem

StreamBurstFacemesh

StreamBurstFacemeshPredictionsItem

StreamBurstJobDetails

StreamBurstLanguage

StreamBurstLanguagePredictionsItem

StreamBurstProsody

StreamBurstProsodyPredictionsItem

StreamData

Configuration used to specify which models should be used and with what settings.

StreamDataModels

Configuration for the language emotion model.

StreamDataModelsFace

Configuration for FACS predictions. If missing or null, no FACS predictions will be generated.

Configuration for Descriptions predictions. If missing or null, no Descriptions predictions will be generated.

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.

Number of frames per second to process. Other frames will be omitted from the response.

1	{
2	"type": "EMBEDDING_GENERATION",
3	"job_id": "string",
4	"request": {
5	"registry_file_details": [
6	{
7	"file_id": "string",
8	"file_url": "string"
9	}
10	]
11	},
12	"state": {
13	"status": "QUEUED",
14	"created_timestamp_ms": 0
15	},
16	"user_id": "string"
17	}

Empathic Voice Interface (EVI)

Expression Measurement API

Custom Models API

Get job details

Path parameters

Response

$	curl https://api.hume.ai/v0/batch/jobs/job_id \
>	-H "X-Hume-Api-Key: <apiKey>"