Azure TTS: The Ultimate Guide to Text-to-Speech with Azure AI Speech

1az account set --subscription "YOUR_SUBSCRIPTION_ID"
2az cognitiveservices account create --name "your-speech-resource" --resource-group "your-resource-group" --kind SpeechServices --sku F0 --location eastus
3

1pip install azure-cognitiveservices-speech
2

1import azure.cognitiveservices.speech as speechsdk
2
3# Replace with your subscription key and region
4speech_key = "YOUR_SPEECH_KEY"
5speech_region = "YOUR_SPEECH_REGION"
6
7# Configure speech synthesis
8speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=speech_region)
9
10# Set the voice name (optional)
11speech_config.speech_synthesis_voice_name = "en-US-JennyNeural"
12
13# Create a speech synthesizer
14speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config)
15
16# The text you want to convert to speech
17text = "Hello, world! This is Azure Text-to-Speech."
18
19# Synthesize the speech
20result = speech_synthesizer.speak_text_async(text).get()
21
22# Check the result
23if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
24    print("Speech synthesized to speaker: {}".format(text))
25elif result.reason == speechsdk.ResultReason.Canceled:
26    cancellation_details = result.cancellation_details
27    print("Speech synthesis canceled: {}".format(cancellation_details.reason))
28    if cancellation_details.reason == speechsdk.CancellationReason.Error:
29        print("Error details: {}".format(cancellation_details.error_details))
30

1<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xml:lang="en-US">
2  <voice name="en-US-JennyNeural">
3    <prosody rate="slow" pitch="+20%">
4      Hello, <emphasis level="strong">world</emphasis>!
5    </prosody>
6  </voice>
7</speak>
8

1const speechConfig = speechsdk.SpeechConfig.fromSubscription("YOUR_SPEECH_KEY", "YOUR_SPEECH_REGION");
2const synthesizer = new speechsdk.SpeechSynthesizer(speechConfig);
3
4synthesizer.speakTextAsync(
5    "Hello, web! This is Azure TTS in action.",
6    result => {
7        if (result.reason === speechsdk.ResultReason.SynthesizingAudioCompleted) {
8            console.log("Speech synthesized to speaker: " + result.audioData.byteLength + " bytes");
9        } else if (result.reason === speechsdk.ResultReason.Canceled) {
10            console.log("Speech synthesis canceled: " + result.errorDetails);
11        }
12        synthesizer.close();
13        synthesizer = null;
14    },
15    error => {
16        console.log("Error synthesizing speech: " + error);
17        synthesizer.close();
18        synthesizer = null;
19    });
20