Copyright (c) 2026 MindMesh Academy. All rights reserved. This content is proprietary and may not be reproduced or distributed without permission.

4.2.2. Azure Speech in Foundry Tools

Azure AI Speech provides speech-to-text and text-to-speech capabilities:

FeatureDescription
Speech-to-TextTranscribe audio to text
Text-to-SpeechGenerate spoken audio from text
Speech TranslationTranslate speech in real-time
Speaker RecognitionIdentify individual speakers
Language IdentificationDetect language being spoken
Voice AssistantsBuild voice-enabled applications
Key Elements:
  • Speech recognition, speaker recognition, and voice assistants are all part of Azure Speech
  • Language identification detects spoken language (compare against supported list)
  • Document translation is NOT part of Speech service (that's Translator)