Azure AI Speech

Introduction

The Azure AI Speech Service provides speech-to-text and text-to-speech capabilities with a Speech resource. You can transcribe speech-to-text with high accuracy, produce natural-sounding text-to-speech voices, translate spoken audio, and use speaker recognition during conversations.

Create custom voices, add specific words to your base vocabulary, or build your own models. Run Speech anywhere, in the cloud or at the edge in containers. It's easy to speech-enable your applications, tools, and devices with the Speech CLI, Speech SDK, Speech Studio, or REST APIs.

Use Azure Speech Services API for:

• Custom Speech: With Custom Speech, you can upload your own data, test and train a custom model, compare accuracy between models, and deploy a model to a custom endpoint. Copy models to other subscriptions if you want colleagues to have access to a model that you built, or if you want to deploy a model to more than one region.

• Batch Transcription: Transcribe audio files as a batch from multiple URLs or an Azure container.

Azure Speech Services API includes such features as:

• Get logs for each endpoint if logs have been requested for that endpoint.

• Request the manifest of the models that you create, to set up on-premises containers.

• Upload data from Azure storage accounts by using a shared access signature (SAS) URI.

• Bring your own storage. Use your own storage accounts for logs, transcription files, and other data.

• Some operations support webhook notifications. You can register your webhooks where notifications are sent.

You can find more details and the supported operation on Azure AI Speech Service | qibb.

How to get started with Azure AI Speech Service integration

Before you begin, ensure that you have the necessary permissions to perform the integration. When you have your Azure AI Speech Service, you can follow the steps below to get started:

1. Obtain your API Key for authentication purposes.

   1. Navigate to your Azure Speech Services directory.
      

      

   2. Choose the Speech App which you want to manage and which credentials you want to use.
      

      

   3. Choose Keys and Endpoint. Your API Key is the value taken from the KEY 1 field. Your Host URL is the host part, taken from the Endpoint field (Example: https://eastus.api.cognitive.microsoft.com). The Host URL you will need if you use a server different than eastus.api.cognitive.microsoft.com. By default the Azure AI Service node support eastus.api.cognitive.microsoft.com host.

      

2. Open the qibb Workflow Editor and click on the Node Catalog button in the right sidebar. Install the Azure AI Speech nodes by clicking on the + button.

3. Drag the Azure AI Speech Service API node, and any other nodes you require from the left sidebar to your flow and connect them.

4. Open the Azure AI Speech Service API node you want to use, select an operation, and add the API Key as part of the apiKey field in the Advanced section. If you are using a Host URL different than the default one (https://eastus.api.cognitive.microsoft.com) then you can fill in the Host input field.
   Now, you can start using the integration!

   

Importing flow examples of a node

Once you've successfully installed a node from the qibb catalog, you can easily import example flows that showcase how the nodes can be used. These example flows are directly accessible within the Flow Editor and are designed to guide users with helpful hints, including how to configure mandatory parameters and credentials.

Here's how to import examples:

1. In the top right corner of the Flow Editor, click on the menu icon.

2. Select Import to open the Import Dialog.

3. Click on the Examples tab.

4. Choose an example from the list.

5. Confirm your selection by clicking on the Import button.

By following these steps, you are now ready to make basic API calls using the provided examples. For further exploration of what’s possible, you can find more complex examples in the Flow Catalog.