NVIDIA releases open-weight Nemotron 3.5 Transcribe: 30B MoE, 40 languages, realtime
flngr · x · 2026-10-29
NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable 30B MoE speech model (4B active parameters) bundling transcription in 40 languages, speaker attribution, translation, contextual prompting, and audio understanding in one checkpoint — and it runs in realtime. Developer andimarafioti showcased a realtime speech-to-speech demo built on it, celebrating the arrival of chunky open-source audio models.
Related event: NVIDIA open-sources Nemotron 3.5 Transcribe speech model(14 posts)→
More from Models
- Developer replaces Siri with local LFM3-Audio-2B, cutting home control latency from 3s to 0.54s — gregbarbosa · 2026-10-29
- 48h of AI chaos: Anthropic IPO, GPT-6.1 Terra, Genie 4, and a Gamma 5 agent demo — dr_cintas · 2026-10-29
- FrontierSWE leaderboard: GPT-6 Astra tops at 65.5%, Gemini 4 Carbon scores 61.2% at 1/16th the cost — scaling01 · 2026-10-29
- DeepSeek Flash fingerprint change hints at migration to a new GPU cluster — teortaxesTex · 2026-10-29
- Google admits human review error in Gemini policy flags, reverses account strikes — RexDouglass · 2026-10-29
- AA-PersonalityBench: Meta's Muse Models Rank Most Friendly, Nemotron 3 Ultra Scores Just 1 — ArtificialAnlys · 2026-10-29