{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/nemotron-voicechat/","md":"https://postcutoff.com/m/nemotron-voicechat/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"nemotron-voicechat","name":"NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B)","org":"NVIDIA","family":"Nemotron Speech","released":"2026-08-03","status":"current","type":"audio/speech","modality_in":["audio"],"modality_out":["audio","text"],"open_weights":true,"model_license":"OpenMDW-1.1","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","model_id":"nvidia/NVIDIA-NemotronLabs-VoiceChat-11B","url":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B"},{"provider":"Hugging Face","model_id":"nvidia/personaplex-7b-v1","url":"https://huggingface.co/nvidia/personaplex-7b-v1"},{"provider":"arXiv","url":"https://arxiv.org/abs/2609.21967"}],"capabilities":[{"name":"Open full-duplex speech model with tool calling","detail":"End-to-end (FastConformer encoder + Nemotron Nano v2 9B + TTS decoder, 11B total) full-duplex voice chat that calls tools mid-conversation; NVIDIA calls it the first open full-duplex model to support tool calling. BFCL-v3 (AU Harness) 56.1%, Full-Duplex-Bench v3 tool selection 82.5%.","first":true,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B"},{"name":"Natural turn-taking","detail":"~450 ms turn-taking latency; #2 among open models on VoiceBench and Full-Duplex-Bench 1.0 (smooth turn-taking 0.82, interruption latency 480 ms).","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B"},{"name":"PersonaPlex: persona + voice prompted full duplex","detail":"PersonaPlex-7B-v1 (2026-01-15), fine-tuned from Kyutai Moshiko, takes a voice prompt and a text persona/role prompt.","first":false,"discovered":"later","source":"https://huggingface.co/nvidia/personaplex-7b-v1"}],"entry":"2026-08-03-nvidia-nemotronlabs-voicechat","notes":"English only. Requires datacenter GPU (A100/H100/H200/B100/B200 or RTX 6000). 'First' is NVIDIA's claim on the model card. HF card release date 2026-08-03; arXiv paper 2609.21967 (Sept 2026).","verified":"2026-09-29","body_md":"Sources: https://huggingface.co/nvidia/NVIDIA-NemotronLabs-VoiceChat-11B , https://huggingface.co/nvidia/personaplex-7b-v1","page_url":"https://postcutoff.com/m/nemotron-voicechat/","standing":{"kind":"speech and audio","newer_count":38,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"nvidia-magpie-tts-multilingual","name":"NVIDIA MagpieTTS Multilingual 357M","org":"NVIDIA","released":"2025-12-11","page_url":"https://postcutoff.com/m/nvidia-magpie-tts-multilingual/"},"after":{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},"weights":"public","licence":"OpenMDW-1.1","licence_permissive":false,"summary":"Weights are public. Licence: OpenMDW-1.1. See the licence for commercial terms."}}