Audio / Text-to-Speech / Speech Recognition
Open-source voice AI from Microsoft with both long-form text-to-speech and speech recognition models. The repo highlights 90-minute multi-speaker TTS, 60-minute single-pass ASR, multilingual support, hotwording, and links to docs, Hugging Face, playground, finetuning, and papers.
The page clearly presents an AI voice product/research repo with concrete capabilities, model names, and usage links. It shows both TTS and ASR functionality, long-form audio support, multilingual features, and integration paths that make it useful for AI builders and users.
The crawl does not show installation steps, API details, licensing terms beyond the repo metadata, or enough hands-on examples to tell how easy it is to run locally versus through the linked model pages.
Last evaluated 118 days ago. Current rank #78. Down 58 spots in the rankings.
