NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B)
Speech and audio
nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
Price not published
Model idnvidia/magpie_tts_multilingual_357m
PricePrice not published
Checked29 September 2026
74newer speech and audio models since its release
The 5 newest are listed. All speech and audio models
2 ways to use NVIDIA MagpieTTS Multilingual 357M, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | nvidia/magpie_tts_multilingual_357m |
huggingface.co | |
| Hugging Face collection | huggingface.co |
Price not published.
No price source linked. Checked 29 September 2026.
What its maker marketed at launch, and what people found later, each with its source.
~357-364M-parameter transformer encoder-decoder predicting multi-codebook audio codec tokens; 12 languages (ar, zh, en, fr, de, hi, it, ja, ko, pt, es, vi); 5 built-in English voices; CER 0.34-3.17% across languages per model card; trained on ~54,300 h.
Versions: v2512 (HF repo created 2025-12-11), v2602 (Mar 2026), v2607 (2026-07-21); repo last updated 2026-09-09. Zero-shot voice cloning was deliberately removed ‘for security reasons’. Part of the Nemotron Speech collection with Parakeet ASR, PersonaPlex and NemotronLabs-VoiceChat.
Sources: https://huggingface.co/nvidia/magpie_tts_multilingual_357m , https://huggingface.co/collections/nvidia/nemotron-speech