NVIDIA opens Magpie TTS: 12-language, low-latency voice model you can run yourself
Magpie TTS is a 364-M-parameter, open-weights model that supports twelve languages—including Arabic, Korean and Brazilian Portuguese – and runs on NVIDIA NIM for sub-100 ms inference. Because the weights are public, you can deploy it on-prem, tune latency, and meet strict data-privacy or domain-specific needs.