Featured Demos
- Neural Text to Speech: The Neural Text to Speech capability makes the voices of your apps nearly indistinguishable from recordings of people.
- Conversation Transcription: Support meeting scenarios so participants can equally engage in the discussion.
- Computer Vision: This feature returns information about visual content found in an image by tagging, descriptions, and domain-specific models.
- Language Understanding (LUIS): LUIS provides simple tools that enable you to build your own language models.
- Speaker Recognition: Identify who is speaking against a group of speakers.



