Recognize and synthesize speech

Azure Speech in Foundry Tools is a service that provides speech-related functionality, including:

A speech-to-text API that enables you to implement speech recognition (converting audible spoken words into text).
A text-to-speech API that enables you to implement speech synthesis (converting text into audible speech).

In this exercise, you'll use both of these APIs to implement a voice message assistant.

While this exercise is based on Python, you can develop speech applications using multiple language-specific SDKs; including:

This exercise takes approximately 30 minutes.

Prerequisites

Before starting this exercise, ensure you have:

An active Azure subscription
Visual Studio Code installed
Python version 3.13 or higher installed
Git installed and configured

Create a Microsoft Foundry project

Microsoft Foundry uses projects to organize models, resources, data, and other assets used to develop an AI solution.

In a web browser, open the Microsoft Foundry portal at https://ai.azure.com and sign in using your Azure credentials. Close any tips or quick start panes that are opened the first time you sign in, and if necessary use the Foundry logo at the top left to navigate to the home page.
If it is not already enabled, in the tool bar the top of the page, enable the New Foundry option. Then, if prompted, create a new project with a unique name; expanding the Advanced options area to specify the following settings for your project:
- Foundry resource: Use the default name for your resource (usually {project_name}-resource)
- Subscription: Your Azure subscription
- Resource group: Create or select a resource group
- Region: Select any of the AI Foundry recommended regions
Tip: Make a note of the region you selected. You'll need it later!
Select Create. Wait for your project to be created.
On the home page for your project, note the project endpoint, key, and OpenAI endpoint.

TIP: You're going to need the project key later!

Get the application files from GitHub

The initial application files you'll need to develop the voice application are provided in a GitHub repo.

Open Visual Studio Code.
Open the command palette (Ctrl+Shift+P) and use the Git:clone command to clone the https://github.com/microsoftlearning/mslearn-ai-language repo to a local folder (it doesn't matter which one). Then open it.

You may be prompted to confirm you trust the authors.
After the repo has been cloned, in the Explorer pane, navigate to the folder containing the application code files at /Labfiles/04-azure-speech/Python/voice-mail. The application files include:
- messages (a subfolder containing audio recordings of messages)
- .env (the application configuration file)
- requirements.txt (the Python package dependencies that need to be installed)
- voice-mail.py (the code file for the application)

Configure your application

In Visual Studio Code, view the Extensions pane; and if it is not already installed, install the Python extension.
In the Command Palette, use the command python:select interpreter. Then select an existing environment if you have one, or create a new Venv environment based on your Python 3.1x installation.

Tip: If you are prompted to install dependencies, you can install the ones in the requirements.txt file in the /Labfiles/04-azure-speech/Python/voice-mail folder; but it's OK if you don't - we'll install them later!
In the Explorer pane, right-click the voice-mail folder containing the application files, and select Open in integrated terminal (or open a terminal in the Terminal menu and navigate to the /Labfiles/04-azure-speech/Python/voice-mail folder.)

Note: Opening the terminal in Visual Studio Code will automatically activate the Python environment. You may need to enable running scripts on your system.
Ensure that the terminal is open in the voice-mail folder with the prefix (.venv) to indicate that the Python environment you created is active.
Install the Azure AI Language Text Analytics SDK package and other required packages by running the following command:
```
pip install -r requirements.txt azure-cognitiveservices-speech==1.42.0
```
In the Explorer pane, in the voice-mail folder, select the .env file to open it. Then update the configuration values to include the key and region for your Foundry project.

Important:Be sure to add the region for your resource, not the endpoint!

Save the modified configuration file.

Add code to synthesize speech

In the Explorer pane, in the voice-mail folder, open the voice-mail.py file.
Review the existing code. You will add code to work with the Azure Speech SDK.

Tip: As you add code to the code file, be sure to maintain the correct indentation.
At the top of the code file, under the existing namespace references, find the comment Import namespaces and add the following code to import the namespaces you will need to use the Text Analytics SDK:
```
# import namespaces
import azure.cognitiveservices.speech as speech_sdk
```
In the main function, note that code to load the endpoint and key from the configuration file has already been provided. Then find the comment Create speech_config using key and region, and add the following code to create a Speech Configuration object:
```
# Create speech_config using key and region
speech_config = speech_sdk.SpeechConfig(subscription=speech_key,
                                        region=speech_region)
```
Review the rest of the main function, and note that a loop has been implemented that enables the user to choose one of three options:
1. Record a voice greeting
2. Transcribe messages
3. Exit the application
Find the record_greeting function, which you will implement to record a voice greeting as an audio file.

In the record_greeting function, find the comment Synthesize the greeting message to an audio file, and add the following code to synthesize speech from the text entered by the user and save it as an audio file.

# Synthesize the greeting message to an audio file
output_file = "greeting.wav"
audio_config = speech_sdk.audio.AudioConfig(filename=output_file)
speech_config.speech_synthesis_voice_name = "en-US-Serena:DragonHDLatestNeural"
speech_synthesizer = speech_sdk.SpeechSynthesizer(speech_config=speech_config,
                                                audio_config=audio_config)
result = speech_synthesizer.speak_text_async(greeting_message).get()
if result.reason == speech_sdk.ResultReason.SynthesizingAudioCompleted:
    print(f"Greeting recorded and saved to {output_file}")
    speech_synthesizer = None  # Release the synthesizer resources
    playsound(output_file)
else:
    print("Error recording greeting: {}".format(result.reason))

Save the changes to the code file. Then, in the terminal, enter the following command to run the application:
```
python voice-mail.py
```
When prompted, enter 2 to record a greeting.
Enter a greeting, like Hi. The person you called is not available right now. Leave a message.
Wait while the speech is synthesized and saved as an audio file.

The file is played back automatically, so you can hear the greeting.

Add code to recognize speech

In the voice-mail.py code file, find the transcribe_messages function; which you will implement to transcribe each of the voice messages in the messages subfolder.

The functional already contains code to loop through the files in the messages folder.

In the transcribe_messages function, find the comment Transcribe the audio file, and add the following code to transcribe the audio.

# Transcribe the audio file
audio_config = speech_sdk.audio.AudioConfig(filename=file_path)
speech_recognizer = speech_sdk.SpeechRecognizer(speech_config=speech_config,
                                                audio_config=audio_config)
result = speech_recognizer.recognize_once_async().get()
if result.reason == speech_sdk.ResultReason.RecognizedSpeech:
    print(f"Transcription: {result.text}")
else:
    print("Error transcribing message: {}".format(result.reason))

Save the changes to the code file. Then, in the terminal, enter the following command to run the application:
```
python voice-mail.py
```
When prompted, enter 3 to transcribe messages.
View the transcription for each message.

Each file is played back automatically, so you can hear the message.

Clean up

If you've finished exploring Azure Speech in Foundry Tools, you should delete the resources you have created in this exercise to avoid incurring unnecessary Azure costs.

Open the Azure portal and view the contents of the resource group where you deployed the resources used in this exercise.
On the toolbar, select Delete resource group.
Enter the resource group name and confirm that you want to delete it.

More information

For more information about using the Speech-to-text and Text-to-speech APIs, see the Speech-to-text documentation and Text-to-speech documentation.