Content Analyzers - Get Result

Service:: Azure AI Services

API Version:: 2025-11-01

Get the result of an analysis operation.

GET {endpoint}/contentunderstanding/analyzerResults/{operationId}?api-version=2025-11-01

URI Parameters

Name	In	Required	Type	Description
endpoint	path	True	string (uri)	Content Understanding service endpoint.
operationId	path	True	string	The unique ID of the operation.
api-version	query	True	string minLength: 1	The API version to use for this operation.

Responses

Name	Type	Description
200 OK	ContentAnalyzerAnalyzeOperationStatus	The request has succeeded.
Other Status Codes	Azure.Core.Foundations.ErrorResponse	An unexpected error response. Headers x-ms-error-code: string

Name

Type

Description

200 OK

ContentAnalyzerAnalyzeOperationStatus

The request has succeeded.

Other Status Codes

Azure.Core.Foundations.ErrorResponse

An unexpected error response.

Headers

x-ms-error-code: string

Security

Ocp-Apim-Subscription-Key

Key-based authentication using the access key of the Azure resource.

Type: apiKey
In: header

EntraIdToken

Microsoft Entra ID OAuth2 authentication using an access token.

Type: oauth2
Flow: accessCode
Authorization URL: https://login.microsoftonline.com/common/oauth2/authorize
Token URL: https://login.microsoftonline.com/common/oauth2/token

Scopes

Name	Description
https://cognitiveservices.azure.com/.default

Examples

Get Analysis Result

Sample request

HTTP

GET {endpoint}/contentunderstanding/analyzerResults/3b31320d-8bab-4f88-b19c-2322a7f11034?api-version=2025-11-01

Sample response

Status code:: 200

{
  "id": "3b31320d-8bab-4f88-b19c-2322a7f11034",
  "status": "Succeeded",
  "result": {
    "analyzerId": "myAnalyzer",
    "apiVersion": "2025-11-01",
    "createdAt": "2025-05-01T18:46:36.244Z",
    "contents": [
      {
        "kind": "document",
        "mimeType": "application/pdf",
        "markdown": "# CONTOSO\n\n...",
        "startPageNumber": 1,
        "endPageNumber": 2,
        "unit": "inch",
        "pages": [
          {
            "pageNumber": 1,
            "width": 8.5,
            "height": 11
          },
          {
            "pageNumber": 2,
            "width": 8.5,
            "height": 11
          }
        ],
        "fields": {
          "Company": {
            "type": "string",
            "valueString": "CONTOSO",
            "spans": [
              {
                "offset": 7,
                "length": 2
              }
            ],
            "confidence": 0.95,
            "source": "D(1,5,1,7,1,7,1.5,5,1.5)"
          }
        }
      }
    ]
  }
}

Definitions

Name	Description
AnalyzeResult	Analyze operation result.
ArrayField	Array field extracted from the content.
AudioVisualContent	Audio visual content. Ex. audio/wav, video/mp4.
AudioVisualContentSegment	Detected audio/visual content segment.
Azure.Core.Foundations.Error	The error object.
Azure.Core.Foundations.ErrorResponse	A response containing error details.
Azure.Core.Foundations.InnerError	An object containing more specific information about the error. As per Azure REST API guidelines - https://aka.ms/AzureRestApiGuidelines#handling-errors.
BooleanField	Boolean field extracted from the content.
ContentAnalyzerAnalyzeOperationStatus	Provides status details for analyze operations.
ContentFieldType	Semantic data type of the field value.
ContentSpan	Position of the element in markdown, specified as a character offset and length.
DateField	Date field extracted from the content.
DocumentAnnotation	Annotation in a document, such as a strikethrough or a comment.
DocumentAnnotationComment	Comment associated with a document annotation.
DocumentAnnotationKind	Document annotation kind.
DocumentBarcode	Barcode in a document.
DocumentBarcodeKind	Barcode kind.
DocumentCaption	Caption of a table or figure.
DocumentChartFigure	Figure containing a chart, such as a bar chart, line chart, or pie chart.
DocumentContent	Document content. Ex. text/plain, application/pdf, image/jpeg.
DocumentContentSegment	Detected document content segment.
DocumentFootnote	Footnote of a table or figure.
DocumentFormula	Mathematical formula in a document.
DocumentFormulaKind	Formula kind.
DocumentHyperlink	Hyperlink in a document, such as a link to a web page or an email address.
DocumentLine	Line in a document, consisting of an contiguous sequence of words.
DocumentMermaidFigure	Figure containing a diagram, such as a flowchart or network diagram.
DocumentPage	Content from a document page.
DocumentParagraph	Paragraph in a document, generally consisting of an contiguous sequence of lines with common alignment and spacing.
DocumentSection	Section in a document.
DocumentTable	Table in a document, consisting table cells arranged in a rectangular layout.
DocumentTableCell	Table cell in a document table.
DocumentTableCellKind	Table cell kind.
DocumentWord	Word in a document, consisting of a contiguous sequence of characters. For non-space delimited languages, such as Chinese, Japanese, and Korean, each character is represented as its own word.
IntegerField	Integer field extracted from the content.
JsonField	JSON field extracted from the content.
LengthUnit	Length unit used by the width, height, and source properties.
MediaContentKind	Kind of media content.
NumberField	Number field extracted from the content.
ObjectField	Object field extracted from the content.
OperationState	The status of the operation
SemanticRole	Semantic role of the paragraph.
StringField	String field extracted from the content.
TimeField	Time field extracted from the content.
TranscriptPhrase	Transcript phrase.
TranscriptWord	Transcript word.
UsageDetails	Usage details.

AnalyzeResult

Object

Analyze operation result.

Name	Type	Default value	Description
analyzerId	string minLength: 1 maxLength: 64 pattern: ^[a-zA-Z0-9._-]{1,64}$		The unique identifier of the analyzer.
apiVersion	string		The version of the API used to analyze the document.
contents	MediaContent[]: AudioVisualContent[] DocumentContent[]		The extracted content.
createdAt	string (date-time)		The date and time when the result was created.
stringEncoding	string	codePoint	The string encoding format for content spans in the response. Possible values are 'codePoint', 'utf16', and `utf8`. Default is `codePoint`.")
warnings	Azure.Core.Foundations.Error[]		Warnings encountered while analyzing the document.

ArrayField

Object

Array field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: array	Semantic data type of the field value.
valueArray	ContentField[]: ArrayField[] BooleanField[] DateField[] IntegerField[] JsonField[] NumberField[] ObjectField[] StringField[] TimeField[]	Array field value.

AudioVisualContent

Object

Audio visual content. Ex. audio/wav, video/mp4.

Name	Type	Description
analyzerId	string minLength: 1 maxLength: 64 pattern: ^[a-zA-Z0-9._-]{1,64}$	The analyzer that generated this content.
cameraShotTimesMs	integer[] (int64)	List of camera shot changes in the video, represented by its timestamp in milliseconds. Only if returnDetails is true.
category	string	Classified content category.
endTimeMs	integer (int64)	End time of the content in milliseconds.
fields	object	Extracted fields from the content.
height	integer (int32)	Height of each video frame in pixels, if applicable.
keyFrameTimesMs	integer[] (int64)	List of key frames in the video, represented by its timestamp in milliseconds. Only if returnDetails is true.
kind	string: audioVisual	Content kind.
markdown	string	Markdown representation of the content.
mimeType	string	Detected MIME type of the content. Ex. application/pdf, image/jpeg, etc.
path	string	The path of the content in the input.
segments	AudioVisualContentSegment[]	List of detected content segments. Only if enableSegment is true.
startTimeMs	integer (int64)	Start time of the content in milliseconds.
transcriptPhrases	TranscriptPhrase[]	List of transcript phrases. Only if returnDetails is true.
width	integer (int32)	Width of each video frame in pixels, if applicable.

AudioVisualContentSegment

Object

Detected audio/visual content segment.

Name	Type	Description
category	string	Classified content category.
endTimeMs	integer (int64)	End time of the segment in milliseconds.
segmentId	string	Segment identifier.
span	ContentSpan	Span of the segment in the markdown content.
startTimeMs	integer (int64)	Start time of the segment in milliseconds.

Azure.Core.Foundations.Error

Object

The error object.

Name	Type	Description
code	string	One of a server-defined set of error codes.
details	Azure.Core.Foundations.Error[]	An array of details about specific errors that led to this reported error.
innererror	Azure.Core.Foundations.InnerError	An object containing more specific information than the current object about the error.
message	string	A human-readable representation of the error.
target	string	The target of the error.

Azure.Core.Foundations.ErrorResponse

Object

A response containing error details.

Name	Type	Description
error	Azure.Core.Foundations.Error	The error object.

Azure.Core.Foundations.InnerError

Object

An object containing more specific information about the error. As per Azure REST API guidelines - https://aka.ms/AzureRestApiGuidelines#handling-errors.

Name	Type	Description
code	string	One of a server-defined set of error codes.
innererror	Azure.Core.Foundations.InnerError	Inner error.

BooleanField

Object

Boolean field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: boolean	Semantic data type of the field value.
valueBoolean	boolean	Boolean field value.

ContentAnalyzerAnalyzeOperationStatus

Object

Provides status details for analyze operations.

Name	Type	Description
error	Azure.Core.Foundations.Error	Error object that describes the error when status is "Failed".
id	string	The unique ID of the operation.
result	AnalyzeResult	The result of the operation.
status	OperationState	The status of the operation
usage	UsageDetails	Usage details of the analyze operation.

ContentFieldType

Enumeration

Semantic data type of the field value.

Value	Description
string	Plain text.
date	Date, normalized to ISO 8601 (YYYY-MM-DD) format.
time	Time, normalized to ISO 8601 (hh:mm:ss) format.
number	Number as double precision floating point.
integer	Integer as 64-bit signed integer.
boolean	Boolean value.
array	List of subfields of the same type.
object	Named list of subfields.
json	JSON object.

ContentSpan

Object

Position of the element in markdown, specified as a character offset and length.

Name	Type	Description
length	integer (int32)	Length of the element in markdown, specified in characters.
offset	integer (int32)	Starting position (0-indexed) of the element in markdown, specified in characters.

DateField

Object

Date field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: date	Semantic data type of the field value.
valueDate	string (date)	Date field value, in ISO 8601 (YYYY-MM-DD) format.

DocumentAnnotation

Object

Annotation in a document, such as a strikethrough or a comment.

Name	Type	Description
author	string	Annotation author.
comments	DocumentAnnotationComment[]	Comments associated with the annotation.
createdAt	string (date-time)	Date and time when the annotation was created.
id	string	Annotation identifier.
kind	DocumentAnnotationKind	Annotation kind.
lastModifiedAt	string (date-time)	Date and time when the annotation was last modified.
source	string	Position of the annotation.
spans	ContentSpan[]	Spans of the content associated with the annotation.
tags	string[]	Tags associated with the annotation.

DocumentAnnotationComment

Object

Comment associated with a document annotation.

Name	Type	Description
author	string	Author of the comment.
createdAt	string (date-time)	Date and time when the comment was created.
lastModifiedAt	string (date-time)	Date and time when the comment was last modified.
message	string	Comment message in Markdown.
tags	string[]	Tags associated with the comment.

DocumentAnnotationKind

Enumeration

Document annotation kind.

Value	Description
highlight	Highlight annotation.
strikethrough	Strikethrough annotation.
underline	Underline annotation.
italic	Italic annotation.
bold	Bold annotation.
circle	Circle annotation.
note	Note annotation.

DocumentBarcode

Object

Barcode in a document.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the barcode.
kind	DocumentBarcodeKind	Barcode kind.
source	string	Encoded source that identifies the position of the barcode in the content.
span	ContentSpan	Span of the barcode in the markdown content.
value	string	Barcode value.

DocumentBarcodeKind

Enumeration

Barcode kind.

Value	Description
QRCode	QR code, as defined in ISO/IEC 18004:2015.
PDF417	PDF417, as defined in ISO 15438.
UPCA	GS1 12-digit Universal Product Code.
UPCE	GS1 6-digit Universal Product Code.
Code39	Code 39 barcode, as defined in ISO/IEC 16388:2007.
Code128	Code 128 barcode, as defined in ISO/IEC 15417:2007.
EAN8	GS1 8-digit International Article Number (European Article Number).
EAN13	GS1 13-digit International Article Number (European Article Number).
DataBar	GS1 DataBar barcode.
Code93	Code 93 barcode, as defined in ANSI/AIM BC5-1995.
Codabar	Codabar barcode, as defined in ANSI/AIM BC3-1995.
DataBarExpanded	GS1 DataBar Expanded barcode.
ITF	Interleaved 2 of 5 barcode, as defined in ANSI/AIM BC2-1995.
MicroQRCode	Micro QR code, as defined in ISO/IEC 23941:2022.
Aztec	Aztec code, as defined in ISO/IEC 24778:2008.
DataMatrix	Data matrix code, as defined in ISO/IEC 16022:2006.
MaxiCode	MaxiCode, as defined in ISO/IEC 16023:2000.

DocumentCaption

Object

Caption of a table or figure.

Name	Type	Description
content	string	Content of the caption.
elements	string[]	Child elements of the caption.
source	string	Encoded source that identifies the position of the caption in the content.
span	ContentSpan	Span of the caption in the markdown content.

DocumentChartFigure

Object

Figure containing a chart, such as a bar chart, line chart, or pie chart.

Name	Type	Default value	Description
caption	DocumentCaption		Figure caption.
content			Chart content represented using Chart.js config.
description	string		Description of the figure.
elements	string[]		Child elements of the figure, excluding any caption or footnotes.
footnotes	DocumentFootnote[]		List of figure footnotes.
id	string		Figure identifier.
kind	string: chart	unknown	Figure kind.
role	SemanticRole		Semantic role of the figure.
source	string		Encoded source that identifies the position of the figure in the content.
span	ContentSpan		Span of the figure in the markdown content.

DocumentContent

Object

Document content. Ex. text/plain, application/pdf, image/jpeg.

Name	Type	Description
analyzerId	string minLength: 1 maxLength: 64 pattern: ^[a-zA-Z0-9._-]{1,64}$	The analyzer that generated this content.
annotations	DocumentAnnotation[]	List of annotations in the document. Only if enableAnnotations and returnDetails are true.
category	string	Classified content category.
endPageNumber	integer (int32)	End page number (1-indexed) of the content.
fields	object	Extracted fields from the content.
figures	DocumentFigure[]: DocumentChartFigure[] DocumentMermaidFigure[]	List of figures in the document. Only if enableLayout and returnDetails are true.
hyperlinks	DocumentHyperlink[]	List of hyperlinks in the document. Only if returnDetails are true.
kind	string: document	Content kind.
markdown	string	Markdown representation of the content.
mimeType	string	Detected MIME type of the content. Ex. application/pdf, image/jpeg, etc.
pages	DocumentPage[]	List of pages in the document.
paragraphs	DocumentParagraph[]	List of paragraphs in the document. Only if enableOcr and returnDetails are true.
path	string	The path of the content in the input.
sections	DocumentSection[]	List of sections in the document. Only if enableLayout and returnDetails are true.
segments	DocumentContentSegment[]	List of detected content segments. Only if enableSegment is true.
startPageNumber	integer (int32)	Start page number (1-indexed) of the content.
tables	DocumentTable[]	List of tables in the document. Only if enableLayout and returnDetails are true.
unit	LengthUnit	Length unit used by the width, height, and source properties. For images/tiff, the default unit is pixel. For PDF, the default unit is inch.

DocumentContentSegment

Object

Detected document content segment.

Name	Type	Description
category	string	Classified content category.
endPageNumber	integer (int32)	End page number (1-indexed) of the segment.
segmentId	string	Segment identifier.
span	ContentSpan	Span of the segment in the markdown content.
startPageNumber	integer (int32)	Start page number (1-indexed) of the segment.

DocumentFootnote

Object

Footnote of a table or figure.

Name	Type	Description
content	string	Content of the footnote.
elements	string[]	Child elements of the footnote.
source	string	Encoded source that identifies the position of the footnote in the content.
span	ContentSpan	Span of the footnote in the markdown content.

DocumentFormula

Object

Mathematical formula in a document.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the formula.
kind	DocumentFormulaKind	Formula kind.
source	string	Encoded source that identifies the position of the formula in the content.
span	ContentSpan	Span of the formula in the markdown content.
value	string	LaTex expression describing the formula.

DocumentFormulaKind

Enumeration

Formula kind.

Value	Description
inline	A formula embedded within the content of a paragraph.
display	A formula in display mode that takes up an entire line.

DocumentHyperlink

Object

Hyperlink in a document, such as a link to a web page or an email address.

Name	Type	Description
content	string	Hyperlinked content.
source	string	Position of the hyperlink.
span	ContentSpan	Span of the hyperlink in the markdown content.
url	string	URL of the hyperlink.

DocumentLine

Object

Line in a document, consisting of an contiguous sequence of words.

Name	Type	Description
content	string	Line text.
source	string	Encoded source that identifies the position of the line in the content.
span	ContentSpan	Span of the line in the markdown content.

DocumentMermaidFigure

Object

Figure containing a diagram, such as a flowchart or network diagram.

Name	Type	Default value	Description
caption	DocumentCaption		Figure caption.
content	string		Diagram content represented using Mermaid syntax.
description	string		Description of the figure.
elements	string[]		Child elements of the figure, excluding any caption or footnotes.
footnotes	DocumentFootnote[]		List of figure footnotes.
id	string		Figure identifier.
kind	string: mermaid	unknown	Figure kind.
role	SemanticRole		Semantic role of the figure.
source	string		Encoded source that identifies the position of the figure in the content.
span	ContentSpan		Span of the figure in the markdown content.

DocumentPage

Object

Content from a document page.

Name	Type	Description
angle	number (float) maximum: 180	The general orientation of the content in clockwise direction, measured in degrees between (-180, 180]. Only if enableOcr is true.
barcodes	DocumentBarcode[]	List of barcodes in the page. Only if enableBarcode and returnDetails are true.
formulas	DocumentFormula[]	List of mathematical formulas in the page. Only if enableFormula and returnDetails are true.
height	number (float)	Height of the page.
lines	DocumentLine[]	List of lines in the page. Only if enableOcr and returnDetails are true.
pageNumber	integer (int32) minimum: 1	Page number (1-based).
spans	ContentSpan[]	Span(s) associated with the page in the markdown content.
width	number (float)	Width of the page.
words	DocumentWord[]	List of words in the page. Only if enableOcr and returnDetails are true.

DocumentParagraph

Object

Paragraph in a document, generally consisting of an contiguous sequence of lines with common alignment and spacing.

Name	Type	Description
content	string	Paragraph text.
role	SemanticRole	Semantic role of the paragraph.
source	string	Encoded source that identifies the position of the paragraph in the content.
span	ContentSpan	Span of the paragraph in the markdown content.

DocumentSection

Object

Section in a document.

Name	Type	Description
elements	string[]	Child elements of the section.
span	ContentSpan	Span of the section in the markdown content.

DocumentTable

Object

Table in a document, consisting table cells arranged in a rectangular layout.

Name	Type	Description
caption	DocumentCaption	Table caption.
cells	DocumentTableCell[]	Cells contained within the table.
columnCount	integer (int32) minimum: 1	Number of columns in the table.
footnotes	DocumentFootnote[]	List of table footnotes.
role	SemanticRole	Semantic role of the table.
rowCount	integer (int32) minimum: 1	Number of rows in the table.
source	string	Encoded source that identifies the position of the table in the content.
span	ContentSpan	Span of the table in the markdown content.

DocumentTableCell

Object

Table cell in a document table.

Name	Type	Default value	Description
columnIndex	integer (int32)		Column index of the cell.
columnSpan	integer (int32) minimum: 1	1	Number of columns spanned by this cell.
content	string		Content of the table cell.
elements	string[]		Child elements of the table cell.
kind	DocumentTableCellKind	content	Table cell kind.
rowIndex	integer (int32)		Row index of the cell.
rowSpan	integer (int32) minimum: 1	1	Number of rows spanned by this cell.
source	string		Encoded source that identifies the position of the table cell in the content.
span	ContentSpan		Span of the table cell in the markdown content.

DocumentTableCellKind

Enumeration

Table cell kind.

Value	Description
content	Main content/data.
rowHeader	Description of the row content.
columnHeader	Description the column content.
stubHead	Description of the row headers, usually located at the top left corner of a table.
description	Description of the content in (parts of) the table.

DocumentWord

Object

Word in a document, consisting of a contiguous sequence of characters. For non-space delimited languages, such as Chinese, Japanese, and Korean, each character is represented as its own word.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the word.
content	string	Word text.
source	string	Encoded source that identifies the position of the word in the content.
span	ContentSpan	Span of the word in the markdown content.

IntegerField

Object

Integer field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: integer	Semantic data type of the field value.
valueInteger	integer (int64)	Integer field value.

JsonField

Object

JSON field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: json	Semantic data type of the field value.
valueJson		JSON field value.

LengthUnit

Enumeration

Length unit used by the width, height, and source properties.

Value	Description
pixel	Pixel unit.
inch	Inch unit.

MediaContentKind

Enumeration

Kind of media content.

Value	Description
document	Document content, such as pdf, image, txt, etc.
audioVisual	Audio visual content, such as mp3, mp4, etc.

NumberField

Object

Number field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: number	Semantic data type of the field value.
valueNumber	number (double)	Number field value.

ObjectField

Object

Object field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: object	Semantic data type of the field value.
valueObject	object	Object field value.

OperationState

Enumeration

The status of the operation

Value	Description
NotStarted	The operation has not started.
Running	The operation is in progress.
Succeeded	The operation has completed successfully.
Failed	The operation has failed.
Canceled	The operation has been canceled by the user.

SemanticRole

Enumeration

Semantic role of the paragraph.

Value	Description
pageHeader	Text near the top edge of the page.
pageFooter	Text near the bottom edge of the page.
pageNumber	Page number.
title	Top-level title describing the entire document.
sectionHeading	Sub heading describing a section of the document.
footnote	Note usually placed after the main content on a page.
formulaBlock	Block of formulas, often with shared alignment.

StringField

Object

String field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: string	Semantic data type of the field value.
valueString	string	String field value.

TimeField

Object

Time field extracted from the content.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the field value.
source	string	Encoded source that identifies the position of the field value in the content.
spans	ContentSpan[]	Span(s) associated with the field value in the markdown content.
type	string: time	Semantic data type of the field value.
valueTime	string (time)	Time field value, in ISO 8601 (hh:mm:ss) format.

TranscriptPhrase

Object

Transcript phrase.

Name	Type	Description
confidence	number (float) minimum: 0 maximum: 1	Confidence of predicting the phrase.
endTimeMs	integer (int64)	End time of the phrase in milliseconds.
locale	string	Detected locale of the phrase. Ex. en-US.
span	ContentSpan	Span of the phrase in the markdown content.
speaker	string	Speaker index or name.
startTimeMs	integer (int64)	Start time of the phrase in milliseconds.
text	string	Transcript text.
words	TranscriptWord[]	List of words in the phrase.

TranscriptWord

Object

Transcript word.

Name	Type	Description
endTimeMs	integer (int64)	End time of the word in milliseconds.
span	ContentSpan	Span of the word in the markdown content.
startTimeMs	integer (int64)	Start time of the word in milliseconds.
text	string	Transcript text.

UsageDetails

Object

Usage details.

Name	Type	Description
audioHours	number (float)	The hours of audio processed.
contextualizationTokens	integer (int32)	The number of contextualization tokens consumed for preparing context, generating confidence scores, source grounding, and output formatting.
documentPagesBasic	integer (int32)	The number of document pages processed at the basic level. For documents without explicit pages (ex. txt, html), every 3000 UTF-16 characters is counted as one page.
documentPagesMinimal	integer (int32)	The number of document pages processed at the minimal level. For documents without explicit pages (ex. txt, html), every 3000 UTF-16 characters is counted as one page.
documentPagesStandard	integer (int32)	The number of document pages processed at the standard level. For documents without explicit pages (ex. txt, html), every 3000 UTF-16 characters is counted as one page.
tokens	object	The number of LLM and embedding tokens consumed, grouped by model (ex. GTP 4.1) and type (ex. input, cached input, output).
videoHours	number (float)	The hours of video processed.

Share via

Content Analyzers - Get Result

URI Parameters

Responses

Security

Ocp-Apim-Subscription-Key

EntraIdToken

Scopes

Examples

Get Analysis Result

Sample request

Sample response

Definitions

AnalyzeResult

ArrayField

AudioVisualContent

AudioVisualContentSegment

Azure.Core.Foundations.Error

Azure.Core.Foundations.ErrorResponse

Azure.Core.Foundations.InnerError

BooleanField

ContentAnalyzerAnalyzeOperationStatus

ContentFieldType

ContentSpan

DateField

DocumentAnnotation

DocumentAnnotationComment

DocumentAnnotationKind

DocumentBarcode

DocumentBarcodeKind

DocumentCaption

DocumentChartFigure

DocumentContent

DocumentContentSegment

DocumentFootnote

DocumentFormula

DocumentFormulaKind

DocumentHyperlink

DocumentLine

DocumentMermaidFigure

DocumentPage

DocumentParagraph

DocumentSection

DocumentTable

DocumentTableCell

DocumentTableCellKind

DocumentWord

IntegerField

JsonField

LengthUnit

MediaContentKind

NumberField

ObjectField

OperationState

SemanticRole

StringField

TimeField

TranscriptPhrase

TranscriptWord

UsageDetails