Listeners rate Cartesia's Sonic 3.6 above NVIDIA Magpie TTS.

It comes from Artificial Analysis, an independent benchmark. Listeners hear two clips of the same line without being told which model produced either, and pick the one they prefer. Sonic 3.6 rates above both NVIDIA models on the board, Magpie-Multilingual 357M and Magpie Multilingual.

Yes. NVIDIA ships Magpie TTS Multilingual as its Riva text to speech NIM. Artificial Analysis rates two versions of it, Magpie-Multilingual 357M and the earlier Magpie Multilingual, and Sonic 3.6 rates above both.

44 languages from one model, including English, Spanish, French, German, and Japanese. Accents are calibrated per region rather than bolted onto an English model. NVIDIA lists 12 languages for Magpie TTS Multilingual.

Yes. An instant clone takes 10 seconds of audio and a professional clone takes 30 minutes, both self-serve on the public API rather than behind an access request.

One to two weeks for most teams. Cartesia is integrated into the major voice agent platforms and every model is on the public API, so there is no platform to move onto and nothing to unpick later.