# Nemotron 3.5 Transcribe

Nemotron 3.5 Transcribe is NVIDIA's latest voice model in our dataset, released Oct 28, 2026. Open weights (OpenMDW-1.1). NVIDIA's open-weights speech model for transcription in 40 languages, translation and speaker attribution on recordings up to an hour, released Oct 28, 2026 under the OpenMDW-1.1 license. Verified against vendor sources on Nov 1, 2026.

Primary source (source of record; Agentic Weekly is the fast independent index): https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

Last verified: 2026-11-01 · Evidence: Reported · Canonical: https://theagenticweekly.com/models/nemotron-3-5-transcribe · JSON: https://theagenticweekly.com/api/models/nemotron-3-5-transcribe

## Key facts

| Fact | Value | Source | Label | Anchor |
|---|---|---|---|---|
| Vendor | NVIDIA |  | editorial | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-vendor |
| Released | Oct 28, 2026 | https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B | vendor-reported, confirmed | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-release-date |
| Context window | 65,536 tokens (66K) | https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B | vendor-reported, confirmed | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-context-tokens |
| Input | audio, text | https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B | vendor-reported, confirmed | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-input-modalities |
| Output | text | https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B | vendor-reported, confirmed | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-output-modalities |
| Parameters | 34B total, 4.3B active, Mamba-2–Transformer hybrid mixture-of-experts with audio and speaker encoders | https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B | vendor-reported, confirmed | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-parameters |
| Licence | OpenMDW-1.1 (open weights) | https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B | vendor-reported, confirmed | https://theagenticweekly.com/models/nemotron-3-5-transcribe#fact-license |

## Vendor claims and neutral signals

- Vendor claim (NVIDIA): best open-weights model on the English Open ASR Leaderboard, with a mean WER of 4.71% on its 9 public test sets (results captured Oct 12, 2026). We did not verify this.
- One checkpoint does transcription in 40 languages, translation, speaker attribution (up to eight speakers) and audio Q&A on recordings up to one hour. It is for recorded audio, not live streaming.

## What we tested

Nothing yet. We have not run Nemotron 3.5 Transcribe ourselves, so every fact here is Reported from the sources below.

## Not verified, left out

- Hosted per-minute prices: NVIDIA lists Baseten, DeepInfra and Simplismart endpoints but we did not capture their prices.
- We have not run the model; all scores are NVIDIA's own.

## Alternatives to Nemotron 3.5 Transcribe

Models from other vendors that share at least one of our groups, from each model's sourced facts (not tested by us).

- [Voxtral 3](https://theagenticweekly.com/models/voxtral-3) (Mistral AI): Both in: Voice · Mini Transcribe 3, per minute of audio $0.0035; Small Transcribe 3, per minute of audio $0.004; Mini Transcribe Realtime 3, per minute of audio $0.008; Mini TTS 3, per 1M characters $13; Voice agent API with Mistral Small 4 for reasoning, per minute $0.04; Voice agent API with a larger model, per minute $0.08 (see each line) · released Oct 20, 2026
- [Grok Voice 3.0](https://theagenticweekly.com/models/grok-voice-3-0) (xAI): Both in: Voice · released Oct 14, 2026
- [Gemini 3.8 Flash-Lite TTS](https://theagenticweekly.com/models/gemini-3-8-flash-lite-tts) (Google): Both in: Voice · 8K context · released Sep 22, 2026
- [Gemini 3.8 Flash TTS](https://theagenticweekly.com/models/gemini-3-8-flash-tts) (Google): Both in: Voice · Text input $0.5; Audio output $9 (per 1M tokens) (temporary price until Dec 31, 2026; list Text input $1; Audio output $18) · released Sep 22, 2026
- [Grok Voice Transcribe 2.0](https://theagenticweekly.com/models/grok-voice-transcribe-2-0) (xAI): Both in: Voice · released Sep 17, 2026
- [GPT-Transcribe](https://theagenticweekly.com/models/gpt-transcribe) (OpenAI): Both in: Voice · Transcription $0.0045 (per minute) · released Jul 28, 2026

## Nemotron 3.5 Transcribe FAQ

**When was Nemotron 3.5 Transcribe released?**

NVIDIA released Nemotron 3.5 Transcribe on Oct 28, 2026. Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

**How large is the Nemotron 3.5 Transcribe context window?**

65,536 tokens. Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

**Is Nemotron 3.5 Transcribe open weights?**

Yes. The weights are published under OpenMDW-1.1. Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

**Has Agentic Weekly tested Nemotron 3.5 Transcribe?**

Not yet. Every fact on this page is Reported: read from the linked vendor pages, not measured by us.

## Sources

- [Hugging Face model card: NVIDIA-Nemotron-3.5-Transcribe-30B-A4B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B)
- [NVIDIA research page: Nemotron 3.5 Transcribe](https://research.nvidia.com/labs/nemotron/NVIDIA-Nemotron-3.5-Transcribe/)

Data licence: CC BY 4.0. Data: Agentic Weekly (https://theagenticweekly.com), CC BY 4.0.