Speech Synthesis (Text‑to‑Speech)

Azure Speech Service provides high‑quality text‑to‑speech (TTS) synthesis that converts plain text into natural‑sounding audio in many languages and voices. Integrate speech synthesis into web, mobile, desktop, or IoT applications with a simple REST API or SDKs.

Key Features

• • Over 400 neural voices across 60+ languages
• • Custom voice models (Neural Voice Font)
• • SSML support for fine‑grained control
• • Real‑time streaming & batch synthesis
• • Secure authentication via Azure AD or subscription keys

Quickstart (JavaScript)

const speechConfig = SpeechConfig.fromSubscription("YOUR_KEY","YOUR_REGION");
speechConfig.speechSynthesisVoiceName = "en-US-JennyNeural";
const audioConfig = AudioConfig.fromDefaultSpeakerOutput();
const synthesizer = new SpeechSynthesizer(speechConfig, audioConfig);
synthesizer.speakTextAsync(
    "Hello, Azure Speech!",
    result => console.log(result.audioData),
    err => console.error(err)
);