openai env vars etc

Author: eric-urban

articles/cognitive-services/Speech-Service/includes/common/environment-variables-clu.md

@@ -3,7 +3,7 @@ author: eric-urban
 ms.service: cognitive-services
 ms.subservice: speech-service
 ms.topic: include
-ms.date: 09/14/2022
+ms.date: 02/28/2023
 ms.author: eur
 ---
 

articles/cognitive-services/Speech-Service/includes/common/environment-variables-openai.md

@@ -0,0 +1,73 @@
+---
+author: eric-urban
+ms.service: cognitive-services
+ms.subservice: speech-service
+ms.topic: include
+ms.date: 02/28/2023
+ms.author: eur
+---
+
+Your application must be authenticated to access Cognitive Services resources. For production, use a secure way of storing and accessing your credentials. For example, after you [get a key](~/articles/cognitive-services/cognitive-services-apis-create-account.md#get-the-keys-for-your-resource) for your <a href="https://portal.azure.com/#create/Microsoft.CognitiveServicesSpeechServices"  title="Create a Speech resource"  target="_blank">Speech resource</a>, write it to a new environment variable on the local machine running the application.
+
+> [!TIP]
+> Don't include the key directly in your code, and never post it publicly. See the Cognitive Services [security](../../../security-features.md) article for more authentication options like [Azure Key Vault](../../../use-key-vault.md). 
+
+To set the environment variables, open a console window, and follow the instructions for your operating system and development environment. 
+- To set the `OPEN_AI_KEY` environment variable, replace `your-openai-key` with one of the keys for your resource.
+- To set the `OPEN_AI_ENDPOINT` environment variable, replace `your-openai-endpoint` with one of the regions for your resource.
+- To set the `SPEECH_KEY` environment variable, replace `your-speech-key` with one of the keys for your resource.
+- To set the `SPEECH_REGION` environment variable, replace `your-speech-region` with one of the regions for your resource.
+
+#### [Windows](#tab/windows)
+
+```console
+setx OPEN_AI_KEY your-openai-key
+setx OPEN_AI_ENDPOINT your-openai-endpoint
+setx SPEECH_KEY your-speech-key
+setx SPEECH_REGION your-speech-region
+```
+
+> [!NOTE]
+> If you only need to access the environment variable in the current running console, you can set the environment variable with `set` instead of `setx`.
+
+After you add the environment variables, you may need to restart any running programs that will need to read the environment variable, including the console window. For example, if you are using Visual Studio as your editor, restart Visual Studio before running the example.
+
+#### [Linux](#tab/linux)
+
+```bash
+export OPEN_AI_KEY=your-openai-key
+export OPEN_AI_ENDPOINT=your-openai-endpoint
+export SPEECH_KEY=your-speech-key
+export SPEECH_REGION=your-speech-region
+```
+
+After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
+
+#### [macOS](#tab/macos)
+
+##### Bash
+
+Edit your .bash_profile, and add the environment variables:
+
+```bash
+export OPEN_AI_KEY=your-openai-key
+export OPEN_AI_ENDPOINT=your-openai-endpoint
+export SPEECH_KEY=your-speech-key
+export SPEECH_REGION=your-speech-region
+```
+
+After you add the environment variables, run `source ~/.bash_profile` from your console window to make the changes effective.
+
+##### Xcode
+
+For iOS and macOS development, you set the environment variables in Xcode. For example, follow these steps to set the environment variable in Xcode 13.4.1.
+
+1. Select **Product** > **Scheme** > **Edit scheme**
+1. Select **Arguments** on the **Run** (Debug Run) page
+1. Under **Environment Variables** select the plus (+) sign to add a new environment variable. 
+1. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
+
+Repeat the steps to set other required environment variables.
+
+For more configuration options, see the [Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
+***

articles/cognitive-services/Speech-Service/includes/quickstarts/openai-speech/intro.md

@@ -6,12 +6,14 @@ ms.date: 02/28/2023
 ms.author: eur
 ---
 
-You can run this Python script to converse with Azure OpenAI. Although the experience is a back-and-forth exchange, Azure OpenAI doesn't remember the context of your conversation.
+> [!IMPORTANT]
+> To complete the steps in this guide, access must be granted to the Azure OpenAI service in the desired Azure subscription. Currently, access to this service is granted only by application. You can apply for access to the Azure OpenAI service by completing the form at [https://aka.ms/oai/access](https://aka.ms/oai/access).
+
+In this how-to guide, you can use Speech to converse with Azure OpenAI. The text recognized by the Speech service is sent to Azure OpenAI. The text response from Azure OpenAI is then synthesized by the Speech service.
 
-Speak into the microphone to start a conversation with OpenAI.
+Speak into the microphone to start a conversation with Azure OpenAI.
 - Azure Cognitive Services Speech recognizes your speech and converts it into text (speech-to-text).
 - Your request as text is sent to the Azure OpenAI service.
 - Azure Cognitive Services Speech synthesizes (text-to-speech) the response from Azure OpenAI to the default speaker.
 
-> [!IMPORTANT]
-> To complete the steps in this guide, access must be granted to the Azure OpenAI service in the desired Azure subscription. Currently, access to this service is granted only by application. You can apply for access to the Azure OpenAI service by completing the form at [https://aka.ms/oai/access](https://aka.ms/oai/access). Open an issue on this repo to contact us if you have an issue.
+Although the experience of this example is a back-and-forth exchange, Azure OpenAI doesn't remember the context of your conversation.

articles/cognitive-services/Speech-Service/includes/quickstarts/openai-speech/python.md

@@ -26,6 +26,8 @@ Install the following Python libraries: `os`, `requests`, `json`
 
 ### Set environment variables
 
+This example requires environment variables named `OPEN_AI_KEY`, `OPEN_AI_ENDPOINT`, `SPEECH_KEY`, and `SPEECH_REGION`.
+
 [!INCLUDE [Environment variables](../../common/environment-variables.md)]
 
 ## Recognize speech from a microphone
@@ -157,6 +159,7 @@ Now that you've completed the quickstart, here are some additional consideration
 
 - To change the speech recognition language, replace `en-US` with another [supported language](~/articles/cognitive-services/speech-service/supported-languages.md). For example, `es-ES` for Spanish (Spain). The default language is `en-US` if you don't specify a language. For details about how to identify one of multiple languages that might be spoken, see [language identification](~/articles/cognitive-services/speech-service/language-identification.md). 
 - To change the voice that you hear, replace `en-US-JennyMultilingualNeural` with another [supported voice](~/articles/cognitive-services/speech-service/supported-languages.md#prebuilt-neural-voices). If the voice does not speak the language of the text returned from Azure OpenAI, the Speech service won't output synthesized audio.
+- To use a different [deployed](/azure/cognitive-services/openai/how-to/create-resource#deploy-a-model) Azure OpenAI model, replace `text-davinci-002` with another [model](/azure/cognitive-services/openai/concepts/models#model-summary-table-and-region-availability). For example, `text-davinci-003` for the latest version of the Davinci model.
 - The Azure OpenAI Service also performs content moderation on the prompt inputs and generated outputs. The prompts or responses may be filtered if harmful content is detected. For more information, see the [content filtering](/azure/cognitive-services/openai/concepts/content-filter) article.
 
 ## Clean up resources

articles/cognitive-services/Speech-Service/openai-speech.md

@@ -1,14 +1,14 @@
 ---
 title: "Azure OpenAI speech to speech chat - Speech service"
 titleSuffix: Azure Cognitive Services
-description: In this how-to guide, you can use Speech to converse with OpenAI. Although the experience is a back-and-forth exchange, OpenAI doesn't remember the context of your conversation.
+description: In this how-to guide, you can use Speech to converse with Azure OpenAI. The text recognized by the Speech service is sent to Azure OpenAI. The text response from Azure OpenAI is then synthesized by the Speech service.
 services: cognitive-services
 author: eric-urban
 manager: nitinme
 ms.service: cognitive-services
 ms.subservice: speech-service
 ms.topic: how-to
-ms.date: 02/23/2023
+ms.date: 02/28/2023
 ms.author: eur
 ms.devlang: python
 keywords: speech to text, openai
@@ -22,6 +22,5 @@ keywords: speech to text, openai
 
 ## Next steps
 
-> [!div class="nextstepaction"]
-> [Learn more about Speech](overview.md)
-> [Learn more about Azure OpenAI](/azure/cognitive-services/openai/overview)
+- [Learn more about Speech](overview.md)
+- [Learn more about Azure OpenAI](/azure/cognitive-services/openai/overview)