Spoken

MAI-Transcribe-2 is Microsoft AI’s most capable transcription model yet, designed to deliver fast, accurate speech recognition across a broad range of real-world audio. It supports speaker diarization to distinguish speakers and attribute words to the right person, along with word-level timestamps for precise alignment, search, navigation, and editing. Keyword biasing helps recognize domain-specific terminology, abbreviations, names, and other terms that can be difficult to distinguish from context alone. Developers can choose between configurable transcription styles: a verbatim setting that preserves filler words and false starts for compliance and analysis, or a clean setting that removes fillers for more readable captions, notes, and published transcripts. The model supports code-switching for conversations that naturally move between languages, including blended language pairs such as Hinglish and Spanglish, and can automatically identify the language being spoken.

Riverside (previously "Riverside FM") is an all-in-one AI-powered content creation studio for recording, editing, and streaming high-quality video and audio. Designed for podcasters, marketers, and businesses, Riverside captures 4K video and lossless audio locally for every participant—ensuring crystal-clear quality even with weak connections. Its intuitive text-based editor lets users trim, clean up, and caption recordings directly from the transcript, eliminating the need for complex editing tools. With features like Magic Audio, AI Voice, and VideoDub, creators can polish sound, fix mistakes, and sync lips with AI-generated speech in seconds. Riverside also enables HD live streaming and AI Show Notes for automatic titles, chapters, and keywords that simplify publishing. Whether recording a podcast, webinar, or social clip, Riverside brings professional-grade production within everyone’s reach.