NVIDIA Open-Sources Nemotron 3.5 Transcribe Speech Model

Episode 1 · NVIDIA Open-Sources Nemotron 3.5 Transcribe 30B Speech Model (2026-10-28, 10 posts)

On October 28, NVIDIA open-sourced the speech transcription model Nemotron 3.5 Transcribe (a 30B-total-parameter MoE with roughly 4B active) and released companion NeMo Speech open-weight ASR models. Both set open-source-leading results in third-party benchmarks and can already be deployed on vLLM 0.32.

Confirmed

• NVIDIA officially released Nemotron 3.5 Transcribe, an open-weight, promptable speech transcription model that combines multilingual transcription, speaker diarization, translation, and audio QA in a single model, supporting transcription in 40 languages and translation between English and 31 languages (per @NVIDIAAI).
• Artificial Analysis benchmarks show the model ties for first among open models for non-streaming transcription with a 2.8% WER, alongside a Mistral model.
• Artificial Analysis tested it on a DeepInfra-hosted endpoint: a 75x real-time speed factor, under 1 second to transcribe 1 minute of audio, at $2.00 per 1,000 minutes of audio.
• The vLLM team reports that NVIDIA NeMo Speech's open-weight English ASR model tops the Open ASR Leaderboard: 5.33% WER in English and an average 4.62% WER across 7 languages; the architecture is an audio encoder + Mamba–Transformer hybrid MoE, deployable on vLLM 0.32.

Why it matters

• A single model covering transcription, speaker diarization, translation, and audio QA, combined with open weights and extremely low cost ($2 per 1,000 minutes), dramatically lowers the barrier to high-quality speech transcription.
• The highly efficient MoE design (4B active out of 30B total parameters) delivers 75x real-time speed, demonstrating MoE's engineering viability for the speech modality, and native vLLM support means the community can self-deploy quickly.

• NVIDIA's Nemotron 3.5 Transcribe ties for #1 open-weight STT at 2.8% WER with just 4B active params — ArtificialAnlys · 2026-10-28
• Nemotron 3.5 Transcribe hits 75x speed factor at $2 per 1,000 minutes in AA benchmark — ArtificialAnlys · 2026-10-28
• NVIDIA open-sources Nemotron 3.5 Transcribe: 30B MoE ASR model with ~4B active params — NVIDIAAI · 2026-10-28
• NVIDIA open-sources Nemotron 3.5 Transcribe 30B ASR model; fine-tuning cuts word error rate 45.8% — NVIDIAAI · 2026-10-28
• NVIDIA releases open Nemotron 3.5 Transcribe 30B A4B speech transcription model on Hugging Face — coder543 · 2026-10-28
• NVIDIA NeMo Speech hits 5.33% English / 4.62% multilingual WER among open models — vllm_project · 2026-10-28
• NVIDIA NeMo Speech tops open ASR at 5.33% WER, servable via vLLM 0.32 plugin — vllm_project · 2026-10-28
• NVIDIA launches open-weight 30B MoE transcription model Nemotron 3.5 Transcribe — baseten · 2026-10-28
• NVIDIA open-sources Nemotron 3.5 Transcribe: 40-language speech model topping Open ASR — realmrfakename · 2026-10-28
• NVIDIA Releases Nemotron 3.5 Transcribe: 30B MoE, 40-Language ASR — NVIDIAAI · 2026-10-29

Episode 2 · vLLM Reviews Native Support for NVIDIA Nemotron-3.5-Transcribe (2026-10-28, 2 posts)

A PR under review in vLLM adds native integration for NVIDIA's Nemotron-3.5-Transcribe, including a native audio tower, FP8/NVFP4 inference, and transcription and chat endpoints.

• Nemotron-3.5-Transcribe lands native vLLM integration with FP8/NVFP4 and speculative decoding — aakashgupta · 2026-10-28
• vLLM PR Adds Native Nemotron-3.5-Transcribe Support: Transcription+Chat, FP8/NVFP4 — vllm_project · 2026-10-28