Microsoft Azure Speech Services brings the power of Microsoft's enterprise-grade AI speech technology directly into the Unreal Engine Editor.

KEY FEATURES

• Text-to-Speech (TTS)

Generate natural-sounding speech with 400+ neural voices across 140+ languages. Perfect for prototyping dialogue, creating placeholder audio, or producing final voiceovers.

• Emotional Styles

Add emotion to your voices: cheerful, sad, angry, excited, terrified, whispering, shouting, and 20+ more styles. Adjust intensity with the Style Degree parameter.

• Role-Play Voices

Character-specific voices including Narrator, Boy, Girl, YoungAdult, OlderAdult, and Senior for storytelling and game dialogue.

• Full SSML Support

Fine-tune every aspect of speech with SSML markup: pauses, emphasis, pronunciation, pitch, rate, and volume control.

• Speech-to-Text (STT)

Transcribe audio files with word-level timestamps and speaker diarization.

• Pronunciation Assessment

Evaluate pronunciation accuracy with detailed scores for fluency, completeness, and correctness. Ideal for language learning games.

• Batch Processing

Process multiple texts at once with progress tracking.

• Multiple Audio Formats

Export as WAV (8-48kHz), MP3 (96-192kbps), or OGG Opus.

AZURE FREE TIER

Get started free with 500,000 characters/month for TTS and 5 hours/month for STT.

REQUIREMENTS

- Microsoft Azure account (free tier available)

- Internet connection for API calls

Documentation: Here

Need help or want to share feedback?

• Support: [email protected]

• Report a bug: https://www.pixelsdesign.it/bug-report.html

• Request a feature: https://www.pixelsdesign.it/feature-request.html