NVIDIA releases NemotronLabs VoiceChat 11B, an open full-duplex voice model with tool calling
Partly confirmed
Status
- Claim
Partly confirmed
- Our reporting
- Medium confidence
- Importance
- 3 of 5
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 Astra95 days after its cutoff
- Claude Opus 5.534 days after its cutoff
- Gemini 4 Hydrogen125 days after its cutoff
- Grok 4.764 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 34 days before it.
Key facts
- 11B params; English; OpenMDW-1.1 license
- Tool calling: BFCL-v3 (AU Harness) 56.1%; Full-Duplex-Bench v3 tool selection 82.5%
- Turn-taking ~450 ms; interruption latency 480 ms; smooth turn-taking 0.82 (FDB 1.0)
- Part of NVIDIA’s 2026 Nemotron Speech push: PersonaPlex-7B (Jan, Moshi-based), Nemotron Speech Streaming ASR, Nemotron 3.5 ASR (40 locales, June)
What happened
NVIDIA added an 11B end-to-end full-duplex voice model to its Nemotron Speech collection. It listens and speaks at the same time, and it can call external tools while keeping the conversation going. Before this, open full-duplex models did not do tool calling.
Why it matters
Open full-duplex models (Kyutai Moshi, NVIDIA PersonaPlex) were mostly chat demos. Tool calling makes an open, self-hostable alternative to cascaded ASR→LLM→TTS agents and to closed realtime APIs possible. The “first” is NVIDIA’s own claim. The release date comes from the model card; we found no separate press release.
Sources
3 sources from 2 sites. Numbers match the chips in the text.
3 sources: 3 primary
Primary
- Hugging Face: NVIDIA-NemotronLabs-VoiceChat-11Bhuggingface.co, code
- arXiv 2609.21967: NemotronLabs VoiceChatarxiv.org, paper
- Hugging Face collection: Nemotron Speechhuggingface.co, code
Changes
- Filed