Skip to content

Commit 91b6b4f

Browse files
SaisangSaisang
authored
Merge pull request #1031 from MicrosoftDocs/main
10/25 11:00 AM IST Publish
2 parents edd8070 + 6e01934 commit 91b6b4f

27 files changed

+492
-621
lines changed

‎articles/ai-services/content-safety/overview.md

Lines changed: 26 additions & 43 deletions
Original file line numberDiff line numberDiff line change
@@ -140,49 +140,32 @@ For more information, see [Language support](/azure/ai-services/content-safety/l
140140

141141
### Region availability
142142

143-
To use the Content Safety APIs, you must create your Azure AI Content Safety resource in a supported region. Currently, the Content Safety features are available in the following Azure regions:
144-
145-
| Region | Moderation APIs (text and image) | Moderation APIs (multimodal) (preview) | Prompt Shields | Protected material detection for Text | Protected material detection for Code | Groundedness detection (preview) | Custom categories (rapid) (preview) | Custom categories (standard) (preview) |
146-
|--|-|---|-|--|---|-|-|---|
147-
| Australia East | ✅ | | ✅ | ✅ | ✅ | | ✅ | ✅|
148-
| Brazil South | ✅ | | ✅| ✅ | | | | |
149-
| Canada Central |✅ | | ✅ |✅ | | | | |
150-
| Central India | | | ✅ | ✅ | | | | |
151-
| Canada East | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
152-
| Central US | ✅ | | | ✅ | ✅ | | ✅ | |
153-
| East US | ✅ |✅| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
154-
| East US 2 | ✅ | | ✅ | ✅ | ✅ | ✅| ✅ | |
155-
| France Central | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
156-
| Germany West Central|✅| | ✅| ✅ | | | | |
157-
| India North | | |✅ |✅ | | | | |
158-
| Italy North | ✅ | | ✅| ✅ | | | | |
159-
| Japan East | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
160-
| Japan West | | | | | ✅ | | ✅ | |
161-
| Korea Central | ✅ | | | | | | | |
162-
| North Central US | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
163-
| Norway East |✅ | | | | | | | |
164-
| Poland Central | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
165-
| South Africa North| ✅| | ✅ | ✅ | ✅ | | | |
166-
| South Central US | ✅ | | | | ✅ | | ✅ | |
167-
| South East Asia | | | ✅ | ✅ | | | ✅ | |
168-
| South India | ✅ | | | ✅ | ✅ | | ✅ | |
169-
| Sweden Central | ✅ | | ✅ | ✅ | ✅ | ✅| ✅ | |
170-
| Switzerland North | ✅ | | ✅ | ✅ | | | ✅ | ✅ |
171-
| Switzerland West | ✅ | | ✅ | ✅ | | | ✅ | ✅ |
172-
| UAE North | ✅ | | | | | | | |
173-
| UK South | ✅ | | ✅ | ✅ | | | ✅ | |
174-
| West Europe | ✅ |✅| ✅ | ✅ | ✅ | | ✅ | |
175-
| West US | | | ✅ | ✅ | ✅ | | ✅ | |
176-
| West US 2 | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
177-
| West US 3 | ✅ | | ✅ | ✅ | ✅ | | ✅ | |
178-
| USGov Arizona | ✅ | | ✅ | ✅ | | | | |
179-
| USGov Virginia | ✅ | | ✅ | ✅ | | | | |
180-
181-
182-
183-
184-
185-
143+
To use the Content Safety APIs, you must create your Azure AI Content Safety resource in a supported region. Currently, the Content Safety features are available in the following Azure regions with different API versions:
144+
145+
| Region | Custom Category | Groundedness | Image | Multimodal(Image with Tex) | Incident Response | Prompt Shield | Protected Material (Text) | Protected Material (Code) | Text | Unified API |
146+
|--------------------|--------------------|--------------------|-------|-----------------|-------------------|---------------|---------------------------|---------------------------|------|-------------|
147+
| Australia East | ✅ | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
148+
| Canada East | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
149+
| Central US | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
150+
| East US | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
151+
| East US 2 | | ✅ | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
152+
| France Central | | ✅ | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
153+
| Japan East | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
154+
| North Central US | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
155+
| Poland Central | | | ✅ | | | ✅ | ✅ | ✅ | ✅ | ✅ |
156+
| South Central US | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
157+
| South India | | | ✅ | | ✅ | | ✅ | ✅ | ✅ | ✅ |
158+
| Sweden Central | | ✅ | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
159+
| Switzerland North | ✅ | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
160+
| Switzerland West | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | |
161+
| UAE North | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | |
162+
| UK South | | ✅ | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
163+
| West Europe | | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
164+
| West US | | ✅ | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
165+
| West US 2 | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
166+
| West US 3 | | | ✅ | | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
167+
| FairFax - USGovArizona| | | ✅ | | | ✅ | ✅ | | ✅ | ✅ |
168+
| FairFax - USGovVirginia| | | ✅ | | | ✅ | ✅ | | ✅ | ✅ |
186169

187170
Feel free to [contact us](mailto:[email protected]) if your business needs other regions to be available.
188171

‎articles/ai-services/content-safety/quickstart-groundedness.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -173,7 +173,7 @@ The Groundedness detection API provides the option to include _reasoning_ in the
173173
> [!TIP]
174174
> We only support **Azure OpenAI GPT-4 Turbo (1106-preview)** resources and do not support other GPT types. You have the flexibility to deploy your GPT-4 Turbo (1106-preview) resources in any region. However, to minimize potential latency and avoid any geographical boundary data privacy and risk concerns, we recommend situating them in the same region as your content safety resources. For comprehensive details on data privacy, refer to the [Data, privacy and security guidelines for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy) and [Data, privacy, and security for Azure AI Content Safety](/legal/cognitive-services/content-safety/data-privacy?context=%2Fazure%2Fai-services%2Fcontent-safety%2Fcontext%2Fcontext).
175175
176-
In order to use your Azure OpenAI GPT4-Turbo (1106-preview) resource to enable the reasoning feature, use Managed Identity to allow your Content Safety resource to access the Azure OpenAI resource:
176+
In order to use your Azure OpenAI GPT4o (0513, 0806 version) resource to enable the reasoning feature, use Managed Identity to allow your Content Safety resource to access the Azure OpenAI resource:
177177

178178
[!INCLUDE [openai-account-access](~/reusable-content/ce-skilling/azure/includes/ai-services/content-safety/includes/openai-account-access.md)]
179179

@@ -295,7 +295,7 @@ The parameters in the request body are defined in this table:
295295
| **text** | (Required) The LLM output text to be checked. Character limit: 7,500. | String |
296296
| **groundingSources** | (Required) Uses an array of grounding sources to validate AI-generated text. See [Input requirements](./overview.md#input-requirements) for limits, | String array |
297297
| **reasoning** | (Optional) Set to `true`, the service uses Azure OpenAI resources to provide an explanation. Be careful: using reasoning increases the processing time and incurs extra fees.| Boolean |
298-
| **llmResource** | (Required) If you want to use your own Azure OpenAI GPT4-Turbo (1106-preview) resource to enable reasoning, add this field and include the subfields for the resources used. | String |
298+
| **llmResource** | (Required) If you want to use your own Azure OpenAI GPT4o (0513, 0806 version) resource to enable reasoning, add this field and include the subfields for the resources used. | String |
299299
| - `resourceType `| Specifies the type of resource being used. Currently it only allows `AzureOpenAI`. We only support Azure OpenAI GPT-4 Turbo (1106-preview) resources and do not support other GPT types. | Enum|
300300
| - `azureOpenAIEndpoint `| Your endpoint URL for Azure OpenAI service. | String |
301301
| - `azureOpenAIDeploymentName` | The name of the specific GPT deployment to use. | String|
@@ -356,7 +356,7 @@ The groundedness detection API includes a correction feature that automatically
356356
> Currently, the correction feature supports only **Azure OpenAI GPT-4 Turbo (1106-preview)** resources. To minimize latency and adhere to data privacy guidelines, it's recommended to deploy your GPT-4 Turbo (1106-preview) resources in the same region as your content safety resources. For more details on data privacy, please refer to the [Data, privacy and security guidelines for Azure OpenAI Service](/legal/cognitive-services/openai/data-privacy?context=/azure/ai-services/openai/context/context)
357357
and [Data, privacy, and security for Azure AI Content Safety](/legal/cognitive-services/content-safety/data-privacy?context=/azure/ai-services/content-safety/context/context).
358358
359-
To use your Azure OpenAI GPT4-Turbo (1106-preview) resource for enabling the correction feature, use Managed Identity to allow your Content Safety resource to access the Azure OpenAI resource. Follow the steps in the [earlier section](#connect-your-own-gpt-deployment) to set up the Managed Identity.
359+
To use your Azure OpenAI GPT4o (0513, 0806 version) resource for enabling the correction feature, use Managed Identity to allow your Content Safety resource to access the Azure OpenAI resource. Follow the steps in the [earlier section](#connect-your-own-gpt-deployment) to set up the Managed Identity.
360360
361361
362362
### Make the API request
@@ -449,7 +449,7 @@ The parameters in the request body are defined in this table:
449449
| **text** | (Required) The LLM output text to be checked. Character limit: 7,500. | String |
450450
| **groundingSources** | (Required) Uses an array of grounding sources to validate AI-generated text. See [Input requirements](./overview.md#input-requirements) for limits. | String Array |
451451
| **correction** | (Optional) Set to `true`, the service uses Azure OpenAI resources to provide the corrected text, ensuring consistency with the grounding sources. Be careful: using correction increases the processing time and incurs extra fees.| Boolean |
452-
| **llmResource** | (Required) If you want to use your own Azure OpenAI GPT4-Turbo (1106-preview) resource to enable reasoning, add this field and include the subfields for the resources used. | String |
452+
| **llmResource** | (Required) If you want to use your own Azure OpenAI GPT4o (0513, 0806 version) resource to enable reasoning, add this field and include the subfields for the resources used. | String |
453453
| - `resourceType `| Specifies the type of resource being used. Currently it only allows `AzureOpenAI`. We only support Azure OpenAI GPT-4 Turbo (1106-preview) resources and do not support other GPT types. | Enum|
454454
| - `azureOpenAIEndpoint `| Your endpoint URL for Azure OpenAI service. | String |
455455
| - `azureOpenAIDeploymentName` | The name of the specific GPT deployment to use. | String|

‎articles/ai-services/speech-service/fast-transcription-create.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ The fast transcription API is a REST API that uses multipart/form-data to submit
3737

3838
Construct the request body according to the following instructions:
3939

40-
- Set the required `locales` property. This value should match the expected locale of the audio data to transcribe. The supported locales are: en-US, es-ES, es-MX, fr-FR, hi-IN, it-IT, ja-JP, ko-KR, pt-BR, and zh-CN. You can only specify one locale per transcription request.
40+
- Set the required `locales` property. This value should match the expected locale of the audio data to transcribe. The supported locales are: de-DE, en-IN, en-US, es-ES, es-MX, fr-FR, hi-IN, it-IT, ja-JP, ko-KR, pt-BR, and zh-CN. Learn more from [Speech service language support](language-support.md?tabs=stt). You can get the latest supported languages via the Rest API [Transcriptions - List Supported Locales](/rest/api/speechtotext/transcriptions/list-supported-locales)
4141
- Optionally, set the `profanityFilterMode` property to specify how to handle profanity in recognition results. Accepted values are `None` to disable profanity filtering, `Masked` to replace profanity with asterisks, `Removed` to remove all profanity from the result, or `Tags` to add profanity tags. The default value is `Masked`. The `profanityFilterMode` property works the same way as via the [batch transcription API](./batch-transcription.md).
4242
- Optionally, set the `channels` property to specify the zero-based indices of the channels to be transcribed separately. If not specified, multiple channels are merged and transcribed jointly. Only up to two channels are supported. If you want to transcribe the channels from a stereo audio file separately, you need to specify `[0,1]` here. Otherwise, stereo audio will be merged to mono, mono audio will be left as is, and only a single channel will be transcribed. In either of the latter cases, the output has no channel indices for the transcribed text, since only a single audio stream is transcribed.
4343
- Optionally, set the `diarizationSettings` property to recognize and separate multiple speakers on mono channel audio file. You need to specify the minimum and maximum number of people who might be speaking in the audio file (for example, specify `"diarizationSettings": {"minSpeakers": 1, "maxSpeakers": 4}`). Then the transcription file will contain a `speaker` entry for each transcribed phrase. The feature isn't available with stereo audio when you set the `channels` property as `[0,1]`.

0 commit comments

Comments
 (0)