NVIDIA open-sources Nemotron 3.5 Transcribe: 40-language ASR with speaker labels, tops VoiceArena
kimmonismus · x · 2026-10-29
NVIDIA released Nemotron 3.5 Transcribe, an open speech model that transcribes hour-long recordings, labels up to 8 speakers, translates between English and 31 languages, and answers questions about the audio.
- Transcription in 40 languages; speaker labels in 13 languages
- Custom names/technical terms can guide the transcript; audio Q&A trained in English
- 30B parameters, 4B active per token, runs on your own NVIDIA GPU
- Tops Hugging Face's English Open ASR leaderboard among open-weight models and leads VoiceArena's 14-system diarization+ASR test
Built for recorded audio; live streaming uses a separate model.
Related event: NVIDIA open-sources Nemotron 3.5 Transcribe speech model(14 posts)→
More from Models
- ChatGPT users report Computer history broken for weeks despite being on — RileyRalmuto · 2026-10-29
- You.com: agentic search failures are behavior problems, fixed in Nemotron 3.5 Lightning — RichardSocher · 2026-10-29
- How I AI agent bench: Grok Bot wins big at 93%, Claude Duet trails at 79% — lennysan · 2026-10-29
- DeepMind slammed for announcing models weeks before availability amid Gemini Xenon chatter — adonis_singh · 2026-10-29
- Alphabet Q3 call: Gemini Carbon frontier model, MCP apps in Search, AI Mode ads expand — lilyraynyc · 2026-10-29
- gpt-6.1-terra runs 4-hour browser session at ~1 action/second on 10% of quota — prd_008 · 2026-10-29