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
Copy file name to clipboardExpand all lines: articles/ai-services/content-understanding/audio/overview.md
+25-25Lines changed: 25 additions & 25 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,13 +2,12 @@
2
2
title: Azure AI Content Understanding audio overview
3
3
titleSuffix: Azure AI services
4
4
description: Learn about Azure AI Content Understanding audio solutions
5
-
author: jagoerge
6
-
ms.author: lajanuar
5
+
author: laujan
6
+
ms.author: jagoerge
7
7
manager: nitinme
8
8
ms.service: azure-ai-content-understanding
9
9
ms.topic: overview
10
-
ms.date: 05/06/2025
11
-
ms.custom: release-preview-2-cu
10
+
ms.date: 05/19/2025
12
11
---
13
12
14
13
@@ -33,7 +32,7 @@ Here are common scenarios for using Content Understanding with conversational au
33
32
:::image type="content" source="../media/audio/overview/workflow-diagram.png" lightbox="../media/audio/overview/workflow-diagram.png" alt-text="Illustration of Content Understanding audio workflow.":::
34
33
35
34
Content Understanding serves as a cornerstone for Media Asset Management solutions, enabling the following capabilities for audio files:
36
-
35
+
37
36
### Content extraction
38
37
39
38
***Transcription**. Converts conversational audio into searchable and analyzable text-based transcripts in WebVTT format. Customizable fields can be generated from transcription data. Sentence-level and word-level timestamps are available upon request.
@@ -46,7 +45,7 @@ Content Understanding serves as a cornerstone for Media Asset Management solutio
46
45
47
46
***Speaker role detection**. Identifies agent and customer roles within contact center call data.
48
47
49
-
***Multilingual transcription**. Generates multilingual transcripts, applying language/locale per phrase. Deviating from language detection this feature is enabled when no language/locale is specified or language is set to 'auto'.
48
+
***Multilingual transcription**. Generates multilingual transcripts, applying language/locale per phrase. Deviating from language detection this feature is enabled when no language/locale is specified or language is set to `auto`.
***Scenario adaptability**. Adapt the service to your requirements by generating custom fields and extract relevant data.
76
75
77
-
## Content Understanding prebuild audio analyzers
76
+
## Content Understanding prebuilt audio analyzers
78
77
79
-
The prebuild analyzers allow extracting valuable insights into audio content without the need to create an analyzer setup.
78
+
The prebuilt analyzers allow extracting valuable insights into audio content without the need to create an analyzer setup.
80
79
81
80
All audio analyzers generate transcripts in standard WEBVTT format separated by speaker.
82
81
83
82
> [!NOTE]
84
-
> Prebuild analyzers are set to use multilingual transcription and returnDetails enabled!
83
+
> Prebuilt analyzers are set to use multilingual transcription and returnDetails enabled!
85
84
86
-
Content Understanding offers the following prebuild analyzers:
85
+
Content Understanding offers the following prebuilt analyzers:
87
86
88
87
**Post-call analysis (prebuilt-callCenter)**. Analyze call recordings to generate:
89
-
- conversation transcripts with speaker role detection result
90
-
- call summary
91
-
- call sentiment
92
-
- top five articles mentioned
93
-
- list of companies mentioned
94
-
- list of people (name and title/role) mentioned
95
-
- list of relevant call categories
96
-
97
-
**Example result:**
88
+
89
+
* conversation transcripts with speaker role detection result
90
+
* call summary
91
+
* call sentiment
92
+
* top five articles mentioned
93
+
* list of companies mentioned
94
+
* list of people (name and title/role) mentioned
95
+
* list of relevant call categories
96
+
97
+
**Example result:**
98
98
```json
99
99
{
100
100
"id": "bc36da27-004f-475e-b808-8b8aead3b566",
@@ -213,7 +213,7 @@ Content Understanding offers the following prebuild analyzers:
213
213
- conversation transcripts
214
214
- conversation summary
215
215
216
-
**Example result:**
216
+
**Example result:**
217
217
```json
218
218
{
219
219
"id": "9624cc49-b6b3-4ce5-be6c-e895d8c2484d",
@@ -258,11 +258,11 @@ Content Understanding offers the following prebuild analyzers:
258
258
}
259
259
```
260
260
261
-
You can also customize prebuild analyzers for more fine-grained control of the output by defining custom fields. Customization allows you to use the full power of generative models to extract deep insights from the audio. For example, customization allows you to:
262
-
- Generate other insights
263
-
- Control the language of the field extraction output
264
-
- Configure the transcription behavior
265
-
- and more
261
+
You can also customize prebuilt analyzers for more fine-grained control of the output by defining custom fields. Customization allows you to use the full power of generative models to extract deep insights from the audio. For example, customization allows you to:
262
+
263
+
* Generate other insights.
264
+
* Control the language of the field extraction output.
265
+
* Configure the transcription behavior.
266
266
267
267
## Input requirements
268
268
For a detailed list of supported audio formats, refer to our [Service limits and codecs](../service-limits.md) page.
0 commit comments