MAI-Voice in Azure Speech

Try a MAI-Voice voice in the Foundry portal:

1. Go to the Text to speech feature page and select Open in playground.
2. Select a MAI-Voice-2.1-Flash voice from the voice dropdown.
3. Enter sample text in the text box.
4. Select Play to hear the synthesized speech.

Try a MAI-Voice voice in the Foundry portal:

1. Go to the Text to speech feature page and select Open in playground.
2. Select a MAI-Voice-2.1 voice from the voice dropdown.
3. Enter sample text in the text box.
4. Select Play to hear the synthesized speech.

Send an SSML POST request to the cognitiveservices/v1 endpoint of your Speech resource.

Set these environment variables:

export SPEECH_KEY=""
export SPEECH_REGION=""

Run the following command:

curl -X POST \
  "https://${SPEECH_REGION}.tts.speech.microsoft.com/cognitiveservices/v1" \
  --header "Content-Type: application/ssml+xml" \
  --header "X-Microsoft-OutputFormat: audio-24khz-160kbitrate-mono-mp3" \
  --header "Ocp-Apim-Subscription-Key: ${SPEECH_KEY}" \
  --data '
  
    Hello, this is a sample from MAI Voice.
  
' \
  --output output.mp3

On success, an output.mp3 file is saved to the current directory.

Send an SSML POST request to the cognitiveservices/v1 endpoint of your Speech resource.

Set these environment variables:

export SPEECH_KEY=""
export SPEECH_REGION=""

Run the following command:

curl -X POST \
  "https://${SPEECH_REGION}.tts.speech.microsoft.com/cognitiveservices/v1" \
  --header "Content-Type: application/ssml+xml" \
  --header "X-Microsoft-OutputFormat: audio-24khz-160kbitrate-mono-mp3" \
  --header "Ocp-Apim-Subscription-Key: ${SPEECH_KEY}" \
  --data '
  
    Hello, this is a sample from MAI Voice.
  
' \
  --output output.mp3

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for Python, and set the SPEECH_KEY and SPEECH_REGION environment variables.

The following example synthesizes SSML to an MP3 file:

import os

import azure.cognitiveservices.speech as speechsdk

speech_config = speechsdk.SpeechConfig(
    subscription=os.environ["SPEECH_KEY"],
    region=os.environ["SPEECH_REGION"],
)
speech_config.set_speech_synthesis_output_format(
    speechsdk.SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3
)
audio_config = speechsdk.audio.AudioOutputConfig(filename="output.mp3")
synthesizer = speechsdk.SpeechSynthesizer(
    speech_config=speech_config,
    audio_config=audio_config,
)

ssml = """

  
    Hello, this is a sample from MAI Voice.
  

"""

result = synthesizer.speak_ssml_async(ssml).get()
if result.reason != speechsdk.ResultReason.SynthesizingAudioCompleted:
    raise RuntimeError(f"Speech synthesis failed: {result.reason}")

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for Python, and set the SPEECH_KEY and SPEECH_REGION environment variables.

The following example synthesizes SSML to an MP3 file:

import os

import azure.cognitiveservices.speech as speechsdk

speech_config = speechsdk.SpeechConfig(
    subscription=os.environ["SPEECH_KEY"],
    region=os.environ["SPEECH_REGION"],
)
speech_config.set_speech_synthesis_output_format(
    speechsdk.SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3
)
audio_config = speechsdk.audio.AudioOutputConfig(filename="output.mp3")
synthesizer = speechsdk.SpeechSynthesizer(
    speech_config=speech_config,
    audio_config=audio_config,
)

ssml = """

  
    Hello, this is a sample from MAI Voice.
  

"""

result = synthesizer.speak_ssml_async(ssml).get()
if result.reason != speechsdk.ResultReason.SynthesizingAudioCompleted:
    raise RuntimeError(f"Speech synthesis failed: {result.reason}")

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for C#, and set the SPEECH_KEY and SPEECH_REGION environment variables.

The following example synthesizes SSML to an MP3 file:

using System;
using System.IO;
using Microsoft.CognitiveServices.Speech;

var speechConfig = SpeechConfig.FromSubscription(
    Environment.GetEnvironmentVariable("SPEECH_KEY"),
    Environment.GetEnvironmentVariable("SPEECH_REGION")
);
speechConfig.SetSpeechSynthesisOutputFormat(
    SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3
);

using var synthesizer = new SpeechSynthesizer(speechConfig);
const string ssml = """

  
    Hello, this is a sample from MAI Voice.
  

""";

using var result = await synthesizer.SpeakSsmlAsync(ssml);
if (result.Reason != ResultReason.SynthesizingAudioCompleted)
{
    throw new InvalidOperationException($"Speech synthesis failed: {result.Reason}");
}

await File.WriteAllBytesAsync("output.mp3", result.AudioData);

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for C#, and set the SPEECH_KEY and SPEECH_REGION environment variables.

The following example synthesizes SSML to an MP3 file:

using System;
using System.IO;
using Microsoft.CognitiveServices.Speech;

var speechConfig = SpeechConfig.FromSubscription(
    Environment.GetEnvironmentVariable("SPEECH_KEY"),
    Environment.GetEnvironmentVariable("SPEECH_REGION")
);
speechConfig.SetSpeechSynthesisOutputFormat(
    SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3
);

using var synthesizer = new SpeechSynthesizer(speechConfig);
const string ssml = """

  
    Hello, this is a sample from MAI Voice.
  

""";

using var result = await synthesizer.SpeakSsmlAsync(ssml);
if (result.Reason != ResultReason.SynthesizingAudioCompleted)
{
    throw new InvalidOperationException($"Speech synthesis failed: {result.Reason}");
}

await File.WriteAllBytesAsync("output.mp3", result.AudioData);

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for JavaScript:

npm install microsoft-cognitiveservices-speech-sdk

Set the SPEECH_KEY and SPEECH_REGION environment variables. The following Node.js example synthesizes SSML to an MP3 file:

const fs = require("fs");
const sdk = require("microsoft-cognitiveservices-speech-sdk");

const speechConfig = sdk.SpeechConfig.fromSubscription(
  process.env.SPEECH_KEY,
  process.env.SPEECH_REGION
);
speechConfig.speechSynthesisOutputFormat =
  sdk.SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3;

const synthesizer = new sdk.SpeechSynthesizer(speechConfig);
const ssml = `

  
    Hello, this is a sample from MAI Voice.
  
`;

synthesizer.speakSsmlAsync(
  ssml,
  (result) => {
    fs.writeFileSync("output.mp3", Buffer.from(result.audioData));
    synthesizer.close();
  },
  (error) => {
    synthesizer.close();
    throw error;
  }
);

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for JavaScript:

npm install microsoft-cognitiveservices-speech-sdk

Set the SPEECH_KEY and SPEECH_REGION environment variables. The following Node.js example synthesizes SSML to an MP3 file:

const fs = require("fs");
const sdk = require("microsoft-cognitiveservices-speech-sdk");

const speechConfig = sdk.SpeechConfig.fromSubscription(
  process.env.SPEECH_KEY,
  process.env.SPEECH_REGION
);
speechConfig.speechSynthesisOutputFormat =
  sdk.SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3;

const synthesizer = new sdk.SpeechSynthesizer(speechConfig);
const ssml = `

  
    Hello, this is a sample from MAI Voice.
  
`;

synthesizer.speakSsmlAsync(
  ssml,
  (result) => {
    fs.writeFileSync("output.mp3", Buffer.from(result.audioData));
    synthesizer.close();
  },
  (error) => {
    synthesizer.close();
    throw error;
  }
);

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for Java, and set the SPEECH_KEY and SPEECH_REGION environment variables.

The following example synthesizes SSML to an MP3 file:

import com.microsoft.cognitiveservices.speech.ResultReason;
import com.microsoft.cognitiveservices.speech.SpeechConfig;
import com.microsoft.cognitiveservices.speech.SpeechSynthesisOutputFormat;
import com.microsoft.cognitiveservices.speech.SpeechSynthesisResult;
import com.microsoft.cognitiveservices.speech.SpeechSynthesizer;
import java.nio.file.Files;
import java.nio.file.Path;

public class MaiVoiceSynthesis {
    public static void main(String[] args) throws Exception {
        SpeechConfig speechConfig = SpeechConfig.fromSubscription(
            System.getenv("SPEECH_KEY"),
            System.getenv("SPEECH_REGION")
        );
        speechConfig.setSpeechSynthesisOutputFormat(
            SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3
        );

        String ssml = """
            
              
                Hello, this is a sample from MAI Voice.
              
            
            """;

        try (SpeechSynthesizer synthesizer = new SpeechSynthesizer(speechConfig);
             SpeechSynthesisResult result = synthesizer.SpeakSsmlAsync(ssml).get()) {
            if (result.getReason() != ResultReason.SynthesizingAudioCompleted) {
                throw new IllegalStateException(
                    "Speech synthesis failed: " + result.getReason()
                );
            }
            Files.write(Path.of("output.mp3"), result.getAudioData());
        } finally {
            speechConfig.close();
        }
    }
}

On success, an output.mp3 file is saved to the current directory.

Install the Speech SDK for Java, and set the SPEECH_KEY and SPEECH_REGION environment variables.

The following example synthesizes SSML to an MP3 file:

import com.microsoft.cognitiveservices.speech.ResultReason;
import com.microsoft.cognitiveservices.speech.SpeechConfig;
import com.microsoft.cognitiveservices.speech.SpeechSynthesisOutputFormat;
import com.microsoft.cognitiveservices.speech.SpeechSynthesisResult;
import com.microsoft.cognitiveservices.speech.SpeechSynthesizer;
import java.nio.file.Files;
import java.nio.file.Path;

public class MaiVoiceSynthesis {
    public static void main(String[] args) throws Exception {
        SpeechConfig speechConfig = SpeechConfig.fromSubscription(
            System.getenv("SPEECH_KEY"),
            System.getenv("SPEECH_REGION")
        );
        speechConfig.setSpeechSynthesisOutputFormat(
            SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3
        );

        String ssml = """
            
              
                Hello, this is a sample from MAI Voice.
              
            
            """;

        try (SpeechSynthesizer synthesizer = new SpeechSynthesizer(speechConfig);
             SpeechSynthesisResult result = synthesizer.SpeakSsmlAsync(ssml).get()) {
            if (result.getReason() != ResultReason.SynthesizingAudioCompleted) {
                throw new IllegalStateException(
                    "Speech synthesis failed: " + result.getReason()
                );
            }
            Files.write(Path.of("output.mp3"), result.getAudioData());
        } finally {
            speechConfig.close();
        }
    }
}

On success, an output.mp3 file is saved to the current directory.