;
};
export const ZoneContent = ({group, value, options = [], values = [], defaultValue, children}) => {
const optionKey = options.map(option => `${option.id}:${option.title}`).join("|");
const [activePivot, setActivePivot] = useState(defaultValue || values[0]);
const slugify = value => value.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-|-$/g, "");
const resolvePivot = () => {
if (typeof window === "undefined") return defaultValue || values[0];
const params = new URLSearchParams(window.location.search);
const requested = params.get("pivots");
if (requested) {
const requestedIds = requested.split(",").map(value => value.trim()).filter(Boolean);
const match = requestedIds.find(id => values.includes(id));
if (match) return match;
}
const hash = window.location.hash.replace(/^#/, "");
if (hash) {
const match = options.find(option => option.id === hash || slugify(option.title) === hash);
if (match) return match.id;
}
try {
const stored = window.localStorage.getItem(`foundry-zone-pivot:${group}`);
if (values.includes(stored)) return stored;
} catch {
return defaultValue || values[0];
}
return defaultValue || values[0];
};
useEffect(() => {
setActivePivot(resolvePivot());
}, [group, defaultValue, values.join("|"), optionKey]);
useEffect(() => {
const onPivotChange = event => {
if (event.detail?.group === group && values.includes(event.detail.value)) {
setActivePivot(event.detail.value);
}
};
window.addEventListener("foundry-zone-pivot-change", onPivotChange);
return () => window.removeEventListener("foundry-zone-pivot-change", onPivotChange);
}, [group, values.join("|")]);
if (activePivot !== value) return null;
return <>{children};
};
In this quickstart, you try real-time speech to text in [Microsoft Foundry](https://ai.azure.com/?cid=learnDocs).
## Prerequisites
* An Azure subscription. [Create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* A Foundry project. If you need to create a project, see [Create a Microsoft Foundry project](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/create-projects).
## Try real-time speech to text
1. Sign in to [Microsoft Foundry](https://ai.azure.com/?cid=learnDocs). Make sure the **New Foundry** toggle is on. These steps refer to **Foundry (new)**.
1. Select **Build** from the top right menu.
2. Select **Models** on the left pane.
3. The **AI Services** tab shows the Foundry models that can be used out of the box in the Foundry portal. Select **Azure Speech - Speech to text** to open the Speech to Text playground.
4. Optionally use the **Parameters** section to change the task, language, profanity policy, and other settings. You can also add special instructions for the LLM.
5. Use the **Upload files** section to select your audio file. Then select **Start**.
6. View the transcription output in the **Transcript** tab. Optionally view the raw API response output in the **JSON** tab.
7. Switch to the **Code** tab to get the sample code for using the speech to text feature in your application.
## Other Foundry (new) features
The following Speech features are available in the Foundry (new) portal:
* [Speech MCP server](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/azure-ai-speech)
* [Speech to text quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-speech-to-text)
* [Text to speech quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-text-to-speech)
* [Text to speech avatar quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/text-to-speech-avatar/batch-synthesis-avatar)
* [Voice live quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/voice-live-quickstart)
1. Sign in to [Microsoft Foundry](https://ai.azure.com/?cid=learnDocs). Make sure the **New Foundry** toggle is off. These steps refer to **Foundry (classic)**.
1. Select **Playgrounds** from the left pane and then select a playground to use. In this example, select **Try the Speech playground**.
1. Select **Real-time transcription**.
2. Select **Show advanced options** to configure speech to text options such as:
* **Language identification**: Used to identify languages spoken in audio when compared against a list of supported languages. For more information about language identification options such as at-start and continuous recognition, see [Language identification](../../../language-identification).
* **Speaker diarization**: Used to identify and separate speakers in audio. Diarization distinguishes between the different speakers who participate in the conversation. The Speech service provides information about which speaker was speaking a particular part of transcribed speech. For more information about speaker diarization, see the [real-time speech to text with speaker diarization](../../../get-started-stt-diarization) quickstart.
* **Custom endpoint**: Use a deployed model from custom speech to improve recognition accuracy. To use Microsoft's baseline model, leave this set to None. For more information about custom speech, see [Custom Speech](../../../custom-speech-overview).
* **Output format**: Choose between simple and detailed output formats. Simple output includes display format and timestamps. Detailed output includes more formats (such as display, lexical, ITN, and masked ITN), timestamps, and N-best lists.
* **Phrase list**: Improve transcription accuracy by providing a list of known phrases, such as names of people or specific locations. Use commas or semicolons to separate each value in the phrase list. For more information about phrase lists, see [Phrase lists](../../../improve-accuracy-phrase-list).
3. Select an audio file to upload, or record audio in real-time. In this example, we use the `Call1_separated_16k_health_insurance.wav` file that's available in the [Speech SDK repository on GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/raw/master/scenarios/call-center/sampledata/Call1_separated_16k_health_insurance.wav). You can download the file or use your own audio file.
1. You can view the real-time transcription at the bottom of the page.
1. You can select the **JSON** tab to see the JSON output of the transcription. Properties include `Offset`, `Duration`, `RecognitionStatus`, `Display`, `Lexical`, `ITN`, and more.
[Reference documentation](https://learn.microsoft.com/dotnet/api/microsoft.cognitiveservices.speech) | [Package (NuGet)](https://www.nuget.org/packages/Microsoft.CognitiveServices.Speech) | [Additional samples on GitHub](https://aka.ms/speech/github-csharp)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create an AI Services resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and endpoint. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
## Set up the environment
The Speech SDK is available as a [NuGet package](https://www.nuget.org/packages/Microsoft.CognitiveServices.Speech) and implements .NET Standard 2.0. You install the Speech SDK later in this guide. For any other requirements, see [Install the Speech SDK](../../../quickstarts/setup-platform).
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and endpoint, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `ENDPOINT` environment variable, replace *your-endpoint* with one of the endpoints for your resource.
```console theme={null}
setx SPEECH_KEY your-key
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource endpoint, follow the same steps. Set `ENDPOINT` to the endpoint of your resource. For example, `https://YourServiceRegion.api.cognitive.microsoft.com`.
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a microphone
Try out the [Azure Speech in Foundry Tools Toolkit](https://marketplace.visualstudio.com/items?itemName=ms-azureaispeech.azure-ai-speech-toolkit) to easily build and run samples on Visual Studio Code.
Follow these steps to create a console application and install the Speech SDK.
1. Open a command prompt window in the folder where you want the new project. Run this command to create a console application with the .NET CLI.
```dotnetcli theme={null}
dotnet new console
```
This command creates the *Program.cs* file in your project directory.
2. Install the Speech SDK in your new project with the .NET CLI.
```dotnetcli theme={null}
dotnet add package Microsoft.CognitiveServices.Speech
```
3. Replace the contents of *Program.cs* with the following code:
```csharp theme={null}
using System;
using System.IO;
using System.Threading.Tasks;
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Audio;
class Program
{
// This example requires environment variables named "SPEECH_KEY" and "ENDPOINT"
static string speechKey = Environment.GetEnvironmentVariable("SPEECH_KEY");
static string endpoint = Environment.GetEnvironmentVariable("ENDPOINT");
static void OutputSpeechRecognitionResult(SpeechRecognitionResult speechRecognitionResult)
{
switch (speechRecognitionResult.Reason)
{
case ResultReason.RecognizedSpeech:
Console.WriteLine($"RECOGNIZED: Text={speechRecognitionResult.Text}");
break;
case ResultReason.NoMatch:
Console.WriteLine($"NOMATCH: Speech could not be recognized.");
break;
case ResultReason.Canceled:
var cancellation = CancellationDetails.FromResult(speechRecognitionResult);
Console.WriteLine($"CANCELED: Reason={cancellation.Reason}");
if (cancellation.Reason == CancellationReason.Error)
{
Console.WriteLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
Console.WriteLine($"CANCELED: ErrorDetails={cancellation.ErrorDetails}");
Console.WriteLine($"CANCELED: Did you set the speech resource key and endpoint values?");
}
break;
}
}
async static Task Main(string[] args)
{
var speechConfig = SpeechConfig.FromEndpoint(new Uri(endpoint), speechKey);
speechConfig.SpeechRecognitionLanguage = "en-US";
using var audioConfig = AudioConfig.FromDefaultMicrophoneInput();
using var speechRecognizer = new SpeechRecognizer(speechConfig, audioConfig);
Console.WriteLine("Speak into your microphone.");
var speechRecognitionResult = await speechRecognizer.RecognizeOnceAsync();
OutputSpeechRecognitionResult(speechRecognitionResult);
}
}
```
4. To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [Language identification](~/articles/ai-services/speech-service/language-identification).
5. Run your new console application to start speech recognition from a microphone:
```console theme={null}
dotnet run
```
Make sure that you set the `SPEECH_KEY` and `ENDPOINT` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
1. Speak into your microphone when prompted. What you speak should appear as text:
```output theme={null}
Speak into your microphone.
RECOGNIZED: Text=I'm excited to try speech to text.
```
## Remarks
Here are some other considerations:
* This example uses the `RecognizeOnceAsync` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
* To recognize speech from an audio file, use `FromWavFileInput` instead of `FromDefaultMicrophoneInput`:
```csharp theme={null}
using var audioConfig = AudioConfig.FromWavFileInput("YourAudioFile.wav");
```
* For compressed audio files such as MP4, install GStreamer and use `PullAudioInputStream` or `PushAudioInputStream`. For more information, see [How to use compressed input audio](~/articles/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams).
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](/cpp/cognitive-services/speech/) | [Package (NuGet)](https://www.nuget.org/packages/Microsoft.CognitiveServices.Speech) | [Additional samples on GitHub](https://aka.ms/speech/github-cpp)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create an AI Services resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and endpoint. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
## Set up the environment
The Speech SDK is available as a [NuGet package](https://www.nuget.org/packages/Microsoft.CognitiveServices.Speech) and implements .NET Standard 2.0. You install the Speech SDK later in this guide. For other requirements, see [Install the Speech SDK](../../../quickstarts/setup-platform).
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and endpoint, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `ENDPOINT` environment variable, replace *your-endpoint* with one of the endpoints for your resource.
```console theme={null}
setx SPEECH_KEY your-key
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource endpoint, follow the same steps. Set `ENDPOINT` to the endpoint of your resource. For example, `https://YourServiceRegion.api.cognitive.microsoft.com`.
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a microphone
Try out the [Azure Speech in Foundry Tools Toolkit](https://marketplace.visualstudio.com/items?itemName=ms-azureaispeech.azure-ai-speech-toolkit) to easily build and run samples on Visual Studio Code.
Follow these steps to create a console application and install the Speech SDK.
1. Create a new C++ console project in [Visual Studio Community](https://visualstudio.microsoft.com/downloads/) named `SpeechRecognition`.
2. Select **Tools** > **Nuget Package Manager** > **Package Manager Console**. In the **Package Manager Console**, run this command:
```console theme={null}
Install-Package Microsoft.CognitiveServices.Speech
```
3. Replace the contents of `SpeechRecognition.cpp` with the following code:
```cpp theme={null}
#include
#include
#include
using namespace Microsoft::CognitiveServices::Speech;
using namespace Microsoft::CognitiveServices::Speech::Audio;
std::string GetEnvironmentVariable(const char* name);
int main()
{
// This example requires environment variables named "SPEECH_KEY" and "ENDPOINT"
auto speechKey = GetEnvironmentVariable("SPEECH_KEY");
auto endpoint = GetEnvironmentVariable("ENDPOINT");
if (std::string(speechKey).empty() || std::string(endpoint).empty()) {
std::cout << "Please set both SPEECH_KEY and ENDPOINT environment variables." << std::endl;
return -1;
}
auto speechConfig = SpeechConfig::FromEndpoint(endpoint, speechKey);
speechConfig->SetSpeechRecognitionLanguage("en-US");
auto audioConfig = AudioConfig::FromDefaultMicrophoneInput();
auto speechRecognizer = SpeechRecognizer::FromConfig(speechConfig, audioConfig);
std::cout << "Speak into your microphone.\n";
auto result = speechRecognizer->RecognizeOnceAsync().get();
if (result->Reason == ResultReason::RecognizedSpeech)
{
std::cout << "RECOGNIZED: Text=" << result->Text << std::endl;
}
else if (result->Reason == ResultReason::NoMatch)
{
std::cout << "NOMATCH: Speech could not be recognized." << std::endl;
}
else if (result->Reason == ResultReason::Canceled)
{
auto cancellation = CancellationDetails::FromResult(result);
std::cout << "CANCELED: Reason=" << (int)cancellation->Reason << std::endl;
if (cancellation->Reason == CancellationReason::Error)
{
std::cout << "CANCELED: ErrorCode=" << (int)cancellation->ErrorCode << std::endl;
std::cout << "CANCELED: ErrorDetails=" << cancellation->ErrorDetails << std::endl;
std::cout << "CANCELED: Did you set the speech resource key and endpoint values?" << std::endl;
}
}
}
std::string GetEnvironmentVariable(const char* name)
{
#if defined(_MSC_VER)
size_t requiredSize = 0;
(void)getenv_s(&requiredSize, nullptr, 0, name);
if (requiredSize == 0)
{
return "";
}
auto buffer = std::make_unique(requiredSize);
(void)getenv_s(&requiredSize, buffer.get(), requiredSize, name);
return buffer.get();
#else
auto value = getenv(name);
return value ? value : "";
#endif
}
```
4. To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [Language identification](~/articles/ai-services/speech-service/language-identification).
5. To start speech recognition from a microphone, [Build and run](/cpp/build/vscpp-step-2-build) your new console application.
Make sure that you set the `SPEECH_KEY` and `ENDPOINT` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
1. Speak into your microphone when prompted. What you speak should appear as text:
```output theme={null}
Speak into your microphone.
RECOGNIZED: Text=I'm excited to try speech to text.
```
## Remarks
Here are some other considerations:
* This example uses the `RecognizeOnceAsync` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
* To recognize speech from an audio file, use `FromWavFileInput` instead of `FromDefaultMicrophoneInput`:
```cpp theme={null}
auto audioConfig = AudioConfig::FromWavFileInput("YourAudioFile.wav");
```
* For compressed audio files such as MP4, install GStreamer and use `PullAudioInputStream` or `PushAudioInputStream`. For more information, see [How to use compressed input audio](~/articles/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams).
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](https://aka.ms/csspeech/goref) | [Package (Go)](https://pkg.go.dev/github.com/Microsoft/cognitive-services-speech-sdk-go) | [Additional samples on GitHub](https://github.com/microsoft/cognitive-services-speech-sdk-go/tree/master/samples/)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create a Foundry resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and region. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
## Set up the environment
Install the Speech SDK for Go. For requirements and instructions, see [Install the Speech SDK](../../../quickstarts/setup-platform).
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and region, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `SPEECH_REGION` environment variable, replace *your-region* with one of the regions for your resource.
* To set the `ENDPOINT` environment variable, replace `your-endpoint` with the actual endpoint of your Speech resource.
```console theme={null}
setx SPEECH_KEY your-key
setx SPEECH_REGION your-region
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource region, follow the same steps. Set `SPEECH_REGION` to the region of your resource. For example, `westus`. Set `ENDPOINT` to the endpoint of your resource
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a microphone
Follow these steps to create a GO module.
1. Open a command prompt window in the folder where you want the new project. Create a new file named *speech-recognition.go*.
2. Copy the following code into *speech-recognition.go*:
```go theme={null}
package main
import (
"bufio"
"fmt"
"os"
"github.com/Microsoft/cognitive-services-speech-sdk-go/audio"
"github.com/Microsoft/cognitive-services-speech-sdk-go/speech"
)
func sessionStartedHandler(event speech.SessionEventArgs) {
defer event.Close()
fmt.Println("Session Started (ID=", event.SessionID, ")")
}
func sessionStoppedHandler(event speech.SessionEventArgs) {
defer event.Close()
fmt.Println("Session Stopped (ID=", event.SessionID, ")")
}
func recognizingHandler(event speech.SpeechRecognitionEventArgs) {
defer event.Close()
fmt.Println("Recognizing:", event.Result.Text)
}
func recognizedHandler(event speech.SpeechRecognitionEventArgs) {
defer event.Close()
fmt.Println("Recognized:", event.Result.Text)
}
func cancelledHandler(event speech.SpeechRecognitionCanceledEventArgs) {
defer event.Close()
fmt.Println("Received a cancellation: ", event.ErrorDetails)
fmt.Println("Did you set the speech resource key and region values?")
}
func main() {
// This example requires environment variables named "SPEECH_KEY" and "SPEECH_REGION"
speechKey := os.Getenv("SPEECH_KEY")
speechRegion := os.Getenv("SPEECH_REGION")
audioConfig, err := audio.NewAudioConfigFromDefaultMicrophoneInput()
if err != nil {
fmt.Println("Got an error: ", err)
return
}
defer audioConfig.Close()
speechConfig, err := speech.NewSpeechConfigFromSubscription(speechKey, speechRegion)
if err != nil {
fmt.Println("Got an error: ", err)
return
}
defer speechConfig.Close()
speechRecognizer, err := speech.NewSpeechRecognizerFromConfig(speechConfig, audioConfig)
if err != nil {
fmt.Println("Got an error: ", err)
return
}
defer speechRecognizer.Close()
speechRecognizer.SessionStarted(sessionStartedHandler)
speechRecognizer.SessionStopped(sessionStoppedHandler)
speechRecognizer.Recognizing(recognizingHandler)
speechRecognizer.Recognized(recognizedHandler)
speechRecognizer.Canceled(cancelledHandler)
speechRecognizer.StartContinuousRecognitionAsync()
defer speechRecognizer.StopContinuousRecognitionAsync()
bufio.NewReader(os.Stdin).ReadBytes('\n')
}
```
3. Run the following commands to create a *go.mod* file that links to components hosted on GitHub:
```cmd theme={null}
go mod init speech-recognition
go get github.com/Microsoft/cognitive-services-speech-sdk-go
```
Make sure that you set the `SPEECH_KEY` and `SPEECH_REGION` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
1. Build and run the code:
```cmd theme={null}
go build
go run speech-recognition
```
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](https://learn.microsoft.com/java/api/com.microsoft.cognitiveservices.speech) | [Additional samples on GitHub](https://aka.ms/speech/github-java)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create an AI Services resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and endpoint. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
## Set up the environment
To set up your environment, [install the Speech SDK](~/articles/ai-services/speech-service/quickstarts/setup-platform). The sample in this quickstart works with the [Java Runtime](~/articles/ai-services/speech-service/quickstarts/setup-platform).
1. Install [Apache Maven](https://maven.apache.org/install.html). Then run `mvn -v` to confirm successful installation.
2. Create a new `pom.xml` file in the root of your project, and copy the following code into it:
```xml theme={null}
4.0.0com.microsoft.cognitiveservices.speech.samplesquickstart-eclipse1.0.0-SNAPSHOTsrcmaven-compiler-plugin3.7.01.81.8com.microsoft.cognitiveservices.speechclient-sdk1.43.0
```
3. Install the Speech SDK and dependencies.
```console theme={null}
mvn clean dependency:copy-dependencies
```
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and endpoint, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `ENDPOINT` environment variable, replace *your-endpoint* with one of the endpoints for your resource.
```console theme={null}
setx SPEECH_KEY your-key
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource endpoint, follow the same steps. Set `ENDPOINT` to the endpoint of your resource. For example, `https://YourServiceRegion.api.cognitive.microsoft.com`.
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a microphone
Follow these steps to create a console application for speech recognition.
1. Create a new file named *SpeechRecognition.java* in the same project root directory.
2. Copy the following code into *SpeechRecognition.java*:
```java theme={null}
import com.microsoft.cognitiveservices.speech.*;
import com.microsoft.cognitiveservices.speech.audio.AudioConfig;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.Future;
public class SpeechRecognition {
// This example requires environment variables named "SPEECH_KEY" and "ENDPOINT"
private static String speechKey = System.getenv("SPEECH_KEY");
private static String endpoint = System.getenv("ENDPOINT");
public static void main(String[] args) throws InterruptedException, ExecutionException, URISyntaxException {
SpeechConfig speechConfig = SpeechConfig.fromEndpoint(new URI(endpoint), speechKey);
speechConfig.setSpeechRecognitionLanguage("en-US");
recognizeFromMicrophone(speechConfig);
}
public static void recognizeFromMicrophone(SpeechConfig speechConfig) throws InterruptedException, ExecutionException {
AudioConfig audioConfig = AudioConfig.fromDefaultMicrophoneInput();
SpeechRecognizer speechRecognizer = new SpeechRecognizer(speechConfig, audioConfig);
System.out.println("Speak into your microphone.");
Future task = speechRecognizer.recognizeOnceAsync();
SpeechRecognitionResult speechRecognitionResult = task.get();
if (speechRecognitionResult.getReason() == ResultReason.RecognizedSpeech) {
System.out.println("RECOGNIZED: Text=" + speechRecognitionResult.getText());
}
else if (speechRecognitionResult.getReason() == ResultReason.NoMatch) {
System.out.println("NOMATCH: Speech could not be recognized.");
}
else if (speechRecognitionResult.getReason() == ResultReason.Canceled) {
CancellationDetails cancellation = CancellationDetails.fromResult(speechRecognitionResult);
System.out.println("CANCELED: Reason=" + cancellation.getReason());
if (cancellation.getReason() == CancellationReason.Error) {
System.out.println("CANCELED: ErrorCode=" + cancellation.getErrorCode());
System.out.println("CANCELED: ErrorDetails=" + cancellation.getErrorDetails());
System.out.println("CANCELED: Did you set the speech resource key and endpoint values?");
}
}
System.exit(0);
}
}
```
3. To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [Language identification](~/articles/ai-services/speech-service/language-identification).
4. Run your new console application to start speech recognition from a microphone:
```console theme={null}
javac SpeechRecognition.java -cp ".;target\dependency\*"
java -cp ".;target\dependency\*" SpeechRecognition
```
Make sure that you set the `SPEECH_KEY` and `ENDPOINT` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
1. Speak into your microphone when prompted. What you speak should appear as text:
```output theme={null}
Speak into your microphone.
RECOGNIZED: Text=I'm excited to try speech to text.
```
## Remarks
Here are some other considerations:
* This example uses the `RecognizeOnceAsync` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
* To recognize speech from an audio file, use `fromWavFileInput` instead of `fromDefaultMicrophoneInput`:
```java theme={null}
AudioConfig audioConfig = AudioConfig.fromWavFileInput("YourAudioFile.wav");
```
* For compressed audio files such as MP4, install GStreamer and use `PullAudioInputStream` or `PushAudioInputStream`. For more information, see [How to use compressed input audio](~/articles/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams).
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](https://learn.microsoft.com/javascript/api/microsoft-cognitiveservices-speech-sdk/) | [Package (npm)](https://www.npmjs.com/package/microsoft-cognitiveservices-speech-sdk) | [Additional samples on GitHub](https://aka.ms/speech/github-javascript) | [Library source code](https://github.com/Microsoft/cognitive-services-speech-sdk-js)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create a Foundry resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and region. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
You also need a *.wav* audio file on your local machine. You can use your own *.wav* file (up to 30 seconds) or download the [https://crbn.us/whatstheweatherlike.wav](https://crbn.us/whatstheweatherlike.wav) sample file.
## Setup
1. Create a new folder `transcription-quickstart` and go to the quickstart folder with the following command:
```shell theme={null}
mkdir transcription-quickstart && cd transcription-quickstart
```
2. Create the `package.json` with the following command:
```shell theme={null}
npm init -y
```
3. Install the Speech SDK for JavaScript with:
```console theme={null}
npm install microsoft-cognitiveservices-speech-sdk
```
### Retrieve resource information
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and region, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `SPEECH_REGION` environment variable, replace *your-region* with one of the regions for your resource.
* To set the `ENDPOINT` environment variable, replace `your-endpoint` with the actual endpoint of your Speech resource.
```console theme={null}
setx SPEECH_KEY your-key
setx SPEECH_REGION your-region
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource region, follow the same steps. Set `SPEECH_REGION` to the region of your resource. For example, `westus`. Set `ENDPOINT` to the endpoint of your resource
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a file
To transcribe speech from a file:
1. Create a new file named *transcription.js* with the following content:
```javascript theme={null}
import { readFileSync, createReadStream } from "fs";
import { SpeechConfig, AudioConfig, ConversationTranscriber, AudioInputStream } from "microsoft-cognitiveservices-speech-sdk";
// This example requires environment variables named "ENDPOINT" and "SPEECH_KEY"
const speechConfig = SpeechConfig.fromEndpoint(new URL(process.env.ENDPOINT), process.env.SPEECH_KEY);
function fromFile() {
const filename = "katiesteve.wav";
const audioConfig = AudioConfig.fromWavFileInput(readFileSync(filename));
const conversationTranscriber = new ConversationTranscriber(speechConfig, audioConfig);
const pushStream = AudioInputStream.createPushStream();
createReadStream(filename).on('data', function (chunk) {
pushStream.write(chunk.slice());
}).on('end', function () {
pushStream.close();
});
console.log("Transcribing from: " + filename);
conversationTranscriber.sessionStarted = function (s, e) {
console.log("SessionStarted event");
console.log("SessionId:" + e.sessionId);
};
conversationTranscriber.sessionStopped = function (s, e) {
console.log("SessionStopped event");
console.log("SessionId:" + e.sessionId);
conversationTranscriber.stopTranscribingAsync();
};
conversationTranscriber.canceled = function (s, e) {
console.log("Canceled event");
console.log(e.errorDetails);
conversationTranscriber.stopTranscribingAsync();
};
conversationTranscriber.transcribed = function (s, e) {
console.log("TRANSCRIBED: Text=" + e.result.text + " Speaker ID=" + e.result.speakerId);
};
// Start conversation transcription
conversationTranscriber.startTranscribingAsync(function () { }, function (err) {
console.trace("err - starting transcription: " + err);
});
}
fromFile();
```
In *transcription.js*, replace *YourAudioFile.wav* with your own *.wav* file. This example only recognizes speech from a *.wav* file. For information about other audio formats, see [How to use compressed input audio](~/articles/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams). This example supports up to 30 seconds of audio.
To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [Language identification](~/articles/ai-services/speech-service/language-identification).
2. Run your new console application to start speech recognition from a file:
```console theme={null}
node transcription.js
```
Wait a few moments to get the response.
## Output
The speech from the audio file should be output as text:
```output theme={null}
RECOGNIZED: Text=I'm excited to try speech to text.
```
## Remarks
This example uses the `recognizeOnceAsync` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
Recognizing speech from a microphone is not supported in Node.js. It's supported only in a browser-based JavaScript environment. For more information, see the [React sample](https://github.com/Azure-Samples/AzureSpeechReactSample) and the [implementation of speech to text from a microphone](https://github.com/Azure-Samples/AzureSpeechReactSample/blob/main/src/App.js#L29) on GitHub.
The React sample shows design patterns for the exchange and management of authentication tokens. It also shows the capture of audio from a microphone or file for speech to text conversions.
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](https://learn.microsoft.com/python/api/azure-cognitiveservices-speech/) | [Package (PyPi)](https://pypi.org/project/azure-cognitiveservices-speech/) | [Additional samples on GitHub](https://aka.ms/speech/github-python)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create an AI Services resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and endpoint. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
## Set up the environment
The Speech SDK for Python is available as a [Python Package Index (PyPI) module](https://pypi.org/project/azure-cognitiveservices-speech/). The Speech SDK for Python is compatible with Windows, Linux, and macOS.
* For Windows, install the [Microsoft Visual C++ Redistributable for Visual Studio 2015, 2017, 2019, and 2022](/cpp/windows/latest-supported-vc-redist) for your platform. Installing this package for the first time might require a restart.
* On Linux, you must use the x64 target architecture.
Install a version of [Python from 3.7 or later](https://www.python.org/downloads/). For other requirements, see [Install the Speech SDK](../../../quickstarts/setup-platform).
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and endpoint, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `ENDPOINT` environment variable, replace *your-endpoint* with one of the endpoints for your resource.
```console theme={null}
setx SPEECH_KEY your-key
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource endpoint, follow the same steps. Set `ENDPOINT` to the endpoint of your resource. For example, `https://YourServiceRegion.api.cognitive.microsoft.com`.
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a microphone
Try out the [Azure Speech in Foundry Tools Toolkit](https://marketplace.visualstudio.com/items?itemName=ms-azureaispeech.azure-ai-speech-toolkit) to easily build and run samples on Visual Studio Code.
Follow these steps to create a console application.
1. Open a command prompt window in the folder where you want the new project. Create a new file named *speech\_recognition.py*.
2. Run this command to install the Speech SDK:
```console theme={null}
pip install azure-cognitiveservices-speech
```
3. Copy the following code into *speech\_recognition.py*:
```Python theme={null}
import os
import azure.cognitiveservices.speech as speechsdk
def recognize_from_microphone():
# This example requires environment variables named "SPEECH_KEY" and "ENDPOINT"
# Replace with your own subscription key and endpoint, the endpoint is like : "https://YourServiceRegion.api.cognitive.microsoft.com"
speech_config = speechsdk.SpeechConfig(subscription=os.environ.get('SPEECH_KEY'), endpoint=os.environ.get('ENDPOINT'))
speech_config.speech_recognition_language="en-US"
audio_config = speechsdk.audio.AudioConfig(use_default_microphone=True)
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
print("Speak into your microphone.")
speech_recognition_result = speech_recognizer.recognize_once_async().get()
if speech_recognition_result.reason == speechsdk.ResultReason.RecognizedSpeech:
print("Recognized: {}".format(speech_recognition_result.text))
elif speech_recognition_result.reason == speechsdk.ResultReason.NoMatch:
print("No speech could be recognized: {}".format(speech_recognition_result.no_match_details))
elif speech_recognition_result.reason == speechsdk.ResultReason.Canceled:
cancellation_details = speech_recognition_result.cancellation_details
print("Speech Recognition canceled: {}".format(cancellation_details.reason))
if cancellation_details.reason == speechsdk.CancellationReason.Error:
print("Error details: {}".format(cancellation_details.error_details))
print("Did you set the speech resource key and endpoint values?")
recognize_from_microphone()
```
4. To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [language identification](~/articles/ai-services/speech-service/language-identification).
5. Run your new console application to start speech recognition from a microphone:
```console theme={null}
python speech_recognition.py
```
Make sure that you set the `SPEECH_KEY` and `ENDPOINT` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
1. Speak into your microphone when prompted. What you speak should appear as text:
```output theme={null}
Speak into your microphone.
RECOGNIZED: Text=I'm excited to try speech to text.
```
## Remarks
Here are some other considerations:
* This example uses the `recognize_once_async` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
* To recognize speech from an audio file, use `filename` instead of `use_default_microphone`:
```python theme={null}
audio_config = speechsdk.audio.AudioConfig(filename="YourAudioFile.wav")
```
* For compressed audio files such as MP4, install GStreamer and use `PullAudioInputStream` or `PushAudioInputStream`. For more information, see [How to use compressed input audio](~/articles/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams).
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](/objectivec/cognitive-services/speech/) | [Package (download)](https://aka.ms/csspeech/macosbinary) | [Additional samples on GitHub](https://aka.ms/speech/github-objective-c)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create a Foundry resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and region. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
## Set up the environment
The Speech SDK for Swift is distributed as a framework bundle. The framework supports both Objective-C and Swift on both iOS and macOS.
The Speech SDK can be used in Xcode projects as a [CocoaPod](https://cocoapods.org/), or [downloaded directly](https://aka.ms/csspeech/macosbinary) and linked manually. This guide uses a CocoaPod. Install the CocoaPod dependency manager as described in its [installation instructions](https://guides.cocoapods.org/using/getting-started.html).
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and region, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `SPEECH_REGION` environment variable, replace *your-region* with one of the regions for your resource.
* To set the `ENDPOINT` environment variable, replace `your-endpoint` with the actual endpoint of your Speech resource.
```console theme={null}
setx SPEECH_KEY your-key
setx SPEECH_REGION your-region
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource region, follow the same steps. Set `SPEECH_REGION` to the region of your resource. For example, `westus`. Set `ENDPOINT` to the endpoint of your resource
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a microphone
Follow these steps to recognize speech in a macOS application.
1. Clone the [Azure-Samples/cognitive-services-speech-sdk](https://github.com/Azure-Samples/cognitive-services-speech-sdk) repository to get the [Recognize speech from a microphone in Swift on macOS](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/quickstart/swift/macos/from-microphone) sample project. The repository also has iOS samples.
2. Navigate to the directory of the downloaded sample app (`helloworld`) in a terminal.
3. Run the command `pod install`. This command generates a `helloworld.xcworkspace` Xcode workspace containing both the sample app and the Speech SDK as a dependency.
4. Open the `helloworld.xcworkspace` workspace in Xcode.
5. Open the file named *AppDelegate.swift* and locate the `applicationDidFinishLaunching` and `recognizeFromMic` methods as shown here.
```swift theme={null}
import Cocoa
@NSApplicationMain
class AppDelegate: NSObject, NSApplicationDelegate {
var label: NSTextField!
var fromMicButton: NSButton!
var sub: String!
var region: String!
@IBOutlet weak var window: NSWindow!
func applicationDidFinishLaunching(_ aNotification: Notification) {
print("loading")
// load subscription information
sub = ProcessInfo.processInfo.environment["SPEECH_KEY"]
region = ProcessInfo.processInfo.environment["SPEECH_REGION"]
label = NSTextField(frame: NSRect(x: 100, y: 50, width: 200, height: 200))
label.textColor = NSColor.black
label.lineBreakMode = .byWordWrapping
label.stringValue = "Recognition Result"
label.isEditable = false
self.window.contentView?.addSubview(label)
fromMicButton = NSButton(frame: NSRect(x: 100, y: 300, width: 200, height: 30))
fromMicButton.title = "Recognize"
fromMicButton.target = self
fromMicButton.action = #selector(fromMicButtonClicked)
self.window.contentView?.addSubview(fromMicButton)
}
@objc func fromMicButtonClicked() {
DispatchQueue.global(qos: .userInitiated).async {
self.recognizeFromMic()
}
}
func recognizeFromMic() {
var speechConfig: SPXSpeechConfiguration?
do {
try speechConfig = SPXSpeechConfiguration(subscription: sub, region: region)
} catch {
print("error \(error) happened")
speechConfig = nil
}
speechConfig?.speechRecognitionLanguage = "en-US"
let audioConfig = SPXAudioConfiguration()
let reco = try! SPXSpeechRecognizer(speechConfiguration: speechConfig!, audioConfiguration: audioConfig)
reco.addRecognizingEventHandler() {reco, evt in
print("intermediate recognition result: \(evt.result.text ?? "(no result)")")
self.updateLabel(text: evt.result.text, color: .gray)
}
updateLabel(text: "Listening ...", color: .gray)
print("Listening...")
let result = try! reco.recognizeOnce()
print("recognition result: \(result.text ?? "(no result)"), reason: \(result.reason.rawValue)")
updateLabel(text: result.text, color: .black)
if result.reason != SPXResultReason.recognizedSpeech {
let cancellationDetails = try! SPXCancellationDetails(fromCanceledRecognitionResult: result)
print("cancelled: \(result.reason), \(cancellationDetails.errorDetails)")
print("Did you set the speech resource key and region values?")
updateLabel(text: "Error: \(cancellationDetails.errorDetails)", color: .red)
}
}
func updateLabel(text: String?, color: NSColor) {
DispatchQueue.main.async {
self.label.stringValue = text!
self.label.textColor = color
}
}
}
```
6. In *AppDelegate.m*, use the [environment variables that you previously set](#set-environment-variables) for your Speech resource key and region.
```swift theme={null}
sub = ProcessInfo.processInfo.environment["SPEECH_KEY"]
region = ProcessInfo.processInfo.environment["SPEECH_REGION"]
```
7. To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [Language identification](~/articles/ai-services/speech-service/language-identification).
8. To make the debug output visible, select **View** > **Debug Area** > **Activate Console**.
9. Build and run the example code by selecting **Product** > **Run** from the menu or selecting the **Play** button.
Make sure that you set the `SPEECH_KEY` and `SPEECH_REGION` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
After you select the button in the app and say a few words, you should see the text that you spoke on the lower part of the screen. When you run the app for the first time, it prompts you to give the app access to your computer's microphone.
## Remarks
This example uses the `recognizeOnce` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
## Objective-C
The Speech SDK for Objective-C shares client libraries and reference documentation with the Speech SDK for Swift. For Objective-C code examples, see the [recognize speech from a microphone in Objective-C on macOS](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/quickstart/objectivec/macos/from-microphone) sample project in GitHub.
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Reference documentation](https://learn.microsoft.com/javascript/api/microsoft-cognitiveservices-speech-sdk/) | [Package (npm)](https://www.npmjs.com/package/microsoft-cognitiveservices-speech-sdk) | [Additional samples on GitHub](https://aka.ms/speech/github-javascript) | [Library source code](https://github.com/Microsoft/cognitive-services-speech-sdk-js)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create a Foundry resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and region. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
You also need a *.wav* audio file on your local machine. You can use your own *.wav* file (up to 30 seconds) or download the [https://crbn.us/whatstheweatherlike.wav](https://crbn.us/whatstheweatherlike.wav) sample file.
## Setup
1. Create a new folder `transcription-quickstart` and go to the quickstart folder with the following command:
```shell theme={null}
mkdir transcription-quickstart && cd transcription-quickstart
```
2. Create the `package.json` with the following command:
```shell theme={null}
npm init -y
```
3. Update the `package.json` to ECMAScript with the following command:
```shell theme={null}
npm pkg set type=module
```
4. Install the Speech SDK for JavaScript with:
```console theme={null}
npm install microsoft-cognitiveservices-speech-sdk
```
5. You need to install the Node.js type definitions to avoid TypeScript errors. Run the following command:
```shell theme={null}
npm install --save-dev @types/node
```
### Retrieve resource information
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and region, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `SPEECH_REGION` environment variable, replace *your-region* with one of the regions for your resource.
* To set the `ENDPOINT` environment variable, replace `your-endpoint` with the actual endpoint of your Speech resource.
```console theme={null}
setx SPEECH_KEY your-key
setx SPEECH_REGION your-region
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource region, follow the same steps. Set `SPEECH_REGION` to the region of your resource. For example, `westus`. Set `ENDPOINT` to the endpoint of your resource
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a file
To transcribe speech from a file:
1. Create a new file named *transcription.ts* with the following content:
```typescript theme={null}
import { readFileSync } from "fs";
import {
SpeechConfig,
AudioConfig,
SpeechRecognizer,
ResultReason,
CancellationDetails,
CancellationReason,
SpeechRecognitionResult
} from "microsoft-cognitiveservices-speech-sdk";
// This example requires environment variables named "ENDPOINT" and "SPEECH_KEY"
const speechConfig: SpeechConfig = SpeechConfig.fromEndpoint(new URL(process.env.ENDPOINT!), process.env.SPEECH_KEY!);
speechConfig.speechRecognitionLanguage = "en-US";
function fromFile(): void {
const audioConfig: AudioConfig = AudioConfig.fromWavFileInput(readFileSync("YourAudioFile.wav"));
const speechRecognizer: SpeechRecognizer = new SpeechRecognizer(speechConfig, audioConfig);
speechRecognizer.recognizeOnceAsync((result: SpeechRecognitionResult) => {
switch (result.reason) {
case ResultReason.RecognizedSpeech:
console.log(`RECOGNIZED: Text=${result.text}`);
break;
case ResultReason.NoMatch:
console.log("NOMATCH: Speech could not be recognized.");
break;
case ResultReason.Canceled:
const cancellation: CancellationDetails = CancellationDetails.fromResult(result);
console.log(`CANCELED: Reason=${cancellation.reason}`);
if (cancellation.reason === CancellationReason.Error) {
console.log(`CANCELED: ErrorCode=${cancellation.ErrorCode}`);
console.log(`CANCELED: ErrorDetails=${cancellation.errorDetails}`);
console.log("CANCELED: Did you set the speech resource key and region values?");
}
break;
}
speechRecognizer.close();
});
}
fromFile();
```
In *transcription.ts*, replace *YourAudioFile.wav* with your own *.wav* file. This example only recognizes speech from a *.wav* file. For information about other audio formats, see [How to use compressed input audio](~/articles/ai-services/speech-service/how-to-use-codec-compressed-audio-input-streams). This example supports up to 30 seconds of audio.
To change the speech recognition language, replace `en-US` with another [supported language](~/articles/ai-services/speech-service/language-support). For example, use `es-ES` for Spanish (Spain). If you don't specify a language, the default is `en-US`. For details about how to identify one of multiple languages that might be spoken, see [Language identification](~/articles/ai-services/speech-service/language-identification).
2. Create the `tsconfig.json` file to transpile the TypeScript code and copy the following code for ECMAScript.
```json theme={null}
{
"compilerOptions": {
"module": "NodeNext",
"target": "ES2022", // Supports top-level await
"moduleResolution": "NodeNext",
"skipLibCheck": true, // Avoid type errors from node_modules
"strict": true // Enable strict type-checking options
},
"include": ["*.ts"]
}
```
3. Transpile from TypeScript to JavaScript.
```shell theme={null}
tsc
```
This command should produce no output if successful.
4. Run your new console application to start speech recognition from a file:
```console theme={null}
node transcription.js
```
Wait a few moments to get the response.
## Output
The speech from the audio file should be output as text:
```output theme={null}
RECOGNIZED: Text=I'm excited to try speech to text.
```
## Remarks
This example uses the `recognizeOnceAsync` operation to transcribe utterances of up to 30 seconds, or until silence is detected. For information about continuous recognition for longer audio, including multi-lingual conversations, see [How to recognize speech](~/articles/ai-services/speech-service/how-to-recognize-speech).
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
[Speech to text REST API reference](../../rest-speech-to-text) | [Speech to text REST API for short audio reference](../../rest-speech-to-text-short) | [Additional samples on GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk)
In this quickstart, you create and run an application to recognize and transcribe speech to text in real-time.
For fast transcription of audio files, consider using the [fast transcription API.](https://learn.microsoft.com/azure/ai-services/speech-service/fast-transcription-create) Fast transcription API supports features such as language identification and diarization.
To instead transcribe audio files asynchronously, see [What is batch transcription](~/articles/ai-services/speech-service/batch-transcription). If you're not sure which speech to text solution is right for you, see [What is speech to text?](~/articles/ai-services/speech-service/speech-to-text)
## Prerequisites
* An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
* [Create a Foundry resource for Speech](https://portal.azure.com/#create/Microsoft.CognitiveServicesAIFoundry) in the Azure portal.
* Get the Speech resource key and region. After your Speech resource is deployed, select **Go to resource** to view and manage keys.
You also need a *.wav* audio file on your local machine. You can use your own *.wav* file up to 60 seconds or download the [https://crbn.us/whatstheweatherlike.wav](https://crbn.us/whatstheweatherlike.wav) sample file.
### Set environment variables
You need to authenticate your application to access Foundry Tools. This article shows you how to use environment variables to store your credentials. You can then access the environment variables from your code to authenticate your application. For production, use a more secure way to store and access your credentials.
To set the environment variables for your Speech resource key and region, open a console window, and follow the instructions for your operating system and development environment.
* To set the `SPEECH_KEY` environment variable, replace *your-key* with one of the keys for your resource.
* To set the `SPEECH_REGION` environment variable, replace *your-region* with one of the regions for your resource.
* To set the `ENDPOINT` environment variable, replace `your-endpoint` with the actual endpoint of your Speech resource.
```console theme={null}
setx SPEECH_KEY your-key
setx SPEECH_REGION your-region
setx ENDPOINT your-endpoint
```
If you only need to access the environment variables in the current console, you can set the environment variable with `set` instead of `setx`.
After you add the environment variables, you might need to restart any programs that need to read the environment variables, including the console window. For example, if you're using Visual Studio as your editor, restart Visual Studio before you run the example.
##### Bash
Edit your *.bashrc* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
After you add the environment variables, run `source ~/.bashrc` from your console window to make the changes effective.
##### Bash
Edit your *.bash\_profile* file, and add the environment variables:
```bash theme={null}
export SPEECH_KEY=your-key
export SPEECH_REGION=your-region
export ENDPOINT=your-endpoint
```
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**.
2. Select **Arguments** on the **Run** (Debug Run) page.
3. Under **Environment Variables** select the plus (+) sign to add a new environment variable.
4. Enter `SPEECH_KEY` for the **Name** and enter your Speech resource key for the **Value**.
To set the environment variable for your Speech resource region, follow the same steps. Set `SPEECH_REGION` to the region of your resource. For example, `westus`. Set `ENDPOINT` to the endpoint of your resource
For more configuration options, see [the Xcode documentation](https://help.apple.com/xcode/#/dev745c5c974).
## Recognize speech from a file
Open a console window and run the following cURL command. Replace *YourAudioFile.wav* with the path and name of your audio file.
```terminal theme={null}
curl --location --request POST "https://%SPEECH_REGION%.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US&format=detailed" ^
--header "Ocp-Apim-Subscription-Key: %SPEECH_KEY%" ^
--header "Content-Type: audio/wav" ^
--data-binary "@YourAudioFile.wav"
```
```terminal theme={null}
audio_file=@'YourAudioFile.wav'
curl --location --request POST \
"https://${SPEECH_REGION}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US&format=detailed" \
--header "Ocp-Apim-Subscription-Key: ${SPEECH_KEY}" \
--header "Content-Type: audio/wav" \
--data-binary $audio_file
```
```terminal theme={null}
audio_file=@'YourAudioFile.wav'
curl --location --request POST \
"https://${SPEECH_REGION}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US&format=detailed" \
--header "Ocp-Apim-Subscription-Key: ${SPEECH_KEY}" \
--header "Content-Type: audio/wav" \
--data-binary $audio_file
```
***
Make sure that you set the `SPEECH_KEY` and `SPEECH_REGION` [environment variables](#set-environment-variables). If you don't set these variables, the sample fails with an error message.
You should receive a response similar to what is shown here. The `DisplayText` should be the text that was recognized from your audio file. The command recognizes up to 60 seconds of audio and converts it to text.
```output theme={null}
{
"RecognitionStatus": "Success",
"DisplayText": "My voice is my passport, verify me.",
"Offset": 6600000,
"Duration": 32100000
}
```
For more information, see [Speech to text REST API for short audio](../../../rest-speech-to-text-short).
## Clean up resources
You can use the [Azure portal](~/articles/ai-services/multi-service-resource) or [Azure Command Line Interface (CLI)](~/articles/ai-services/multi-service-resource) to remove the Speech resource you created.
## Next step
1. Select **Build** from the top right menu.
2. Select **Models** on the left pane.
3. The **AI Services** tab shows the Foundry models that can be used out of the box in the Foundry portal. Select **Azure Speech - Speech to text** to open the Speech to Text playground.
4. Optionally use the **Parameters** section to change the task, language, profanity policy, and other settings. You can also add special instructions for the LLM.
5. Use the **Upload files** section to select your audio file. Then select **Start**.
6. View the transcription output in the **Transcript** tab. Optionally view the raw API response output in the **JSON** tab.
7. Switch to the **Code** tab to get the sample code for using the speech to text feature in your application.
## Other Foundry (new) features
The following Speech features are available in the Foundry (new) portal:
* [Speech MCP server](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/azure-ai-speech)
* [Speech to text quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-speech-to-text)
* [Text to speech quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/get-started-text-to-speech)
* [Text to speech avatar quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/text-to-speech-avatar/batch-synthesis-avatar)
* [Voice live quickstart](https://learn.microsoft.com/azure/ai-services/speech-service/voice-live-quickstart)
1. Select **Playgrounds** from the left pane and then select a playground to use. In this example, select **Try the Speech playground**.
1. Select **Real-time transcription**.
2. Select **Show advanced options** to configure speech to text options such as:
* **Language identification**: Used to identify languages spoken in audio when compared against a list of supported languages. For more information about language identification options such as at-start and continuous recognition, see [Language identification](../../../language-identification).
* **Speaker diarization**: Used to identify and separate speakers in audio. Diarization distinguishes between the different speakers who participate in the conversation. The Speech service provides information about which speaker was speaking a particular part of transcribed speech. For more information about speaker diarization, see the [real-time speech to text with speaker diarization](../../../get-started-stt-diarization) quickstart.
* **Custom endpoint**: Use a deployed model from custom speech to improve recognition accuracy. To use Microsoft's baseline model, leave this set to None. For more information about custom speech, see [Custom Speech](../../../custom-speech-overview).
* **Output format**: Choose between simple and detailed output formats. Simple output includes display format and timestamps. Detailed output includes more formats (such as display, lexical, ITN, and masked ITN), timestamps, and N-best lists.
* **Phrase list**: Improve transcription accuracy by providing a list of known phrases, such as names of people or specific locations. Use commas or semicolons to separate each value in the phrase list. For more information about phrase lists, see [Phrase lists](../../../improve-accuracy-phrase-list).
3. Select an audio file to upload, or record audio in real-time. In this example, we use the `Call1_separated_16k_health_insurance.wav` file that's available in the [Speech SDK repository on GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/raw/master/scenarios/call-center/sampledata/Call1_separated_16k_health_insurance.wav). You can download the file or use your own audio file.
1. You can view the real-time transcription at the bottom of the page.
1. You can select the **JSON** tab to see the JSON output of the transcription. Properties include `Offset`, `Duration`, `RecognitionStatus`, `Display`, `Lexical`, `ITN`, and more.
