SSyncDev

Nemotron 3.5 Transcribe 30B A4B

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

Nemotron 3.5 Transcribe 30B A4B is NVIDIA's open offline ASR model: 40 languages, hour-long files, word timestamps, diarisation and translation.

Key specifications

Specification score
23.4
Context window
65.54K
License
OpenMDW-1.1

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Weights free under OpenMDW-1.1. OpenRouter lists an audio-based price; confirm the unit and rate on your account.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Audio input

Produces

  • Text output

Capabilities

AudioOpen weights

What is Nemotron 3.5 Transcribe 30B A4B?

An hour of audio in one request, with words, timestamps and speaker turns coming back together. Nemotron 3.5 Transcribe 30B A4B is NVIDIA's open-weight offline speech model, and its pitch is that one checkpoint replaces a recogniser, an aligner and a diarisation pipeline. NVIDIA dates it 28 October 2026.

It is not a streaming model. Audio is encoded internally in 30-second chunks, and the whole file goes in at once.

What is inside

The language model is a hybrid Mamba-2/Transformer mixture-of-experts built on Nemotron 3.5 Lightning 30B A3B. Alongside it runs a parallel encoder: a Transformer ASR encoder plus a speaker encoder. Totals come to about 34B parameters with about 4.3B active, including an audio encoder of roughly 800M.

Numbers

Item Detail
Weights nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B (BF16; FP8 and NVFP4 variants)
Languages 40 for transcription; translation to and from English for a subset
Max recording About one hour
Audio 16 kHz mono; WAV, FLAC, MP3, OGG
Context 65,536 tokens
Extras Word timestamps, speaker diarisation
Licence OpenMDW-1.1

NVIDIA reports a 4.71% mean word error rate on the nine-dataset English Open ASR Leaderboard and 4.62% across its seven-language multilingual set, ahead of Qwen3-ASR-1.7B on both. On long-form English it reports 10.98 against 13.37 for Parakeet-TDT-0.6B-v3. These are publisher numbers.

Getting timestamps out

This is fiddly, so plan for it. In vLLM, start the server with the ctc_timestamp_middleware and --trust-request-mm-kwargs, then send capture_ctc_timestamps: True in the multimodal processor kwargs, with speaker tags such as <spk:0> in the prompt. The response carries a ctc_timestamps object holding words, timings, diarisation segments and the speaker map. Always check its error field.

Constraints: one recording per request, stream=false, n=1. And timestamps do not work with the DFlash2 speculative-decoding option.

For plain transcription, NVIDIA recommends temperature 0 with reasoning off.

Throughput and the closed fast path

NVIDIA's NIM, with NVFP4 and DFlash2 on one RTX PRO 6000 Blackwell, reportedly processes up to 2,238 seconds of audio per second. Those serving optimisations are not open source, and the open vLLM path is expected to be about half as fast. Budget for the open number if you self-host.

The reference deployment is one H100 80GB. Lovelace cards such as the L40S run FP8 only.

Loose ends

The Hugging Face repo was created on 7 October, three weeks before the stated release date, and OpenRouter added it on 29 October as nvidia/nemotron-3.5-transcribe with an audio-based price whose unit we could not confirm. NVIDIA mentions a Transcribe NIM, but the model did not appear in the build.nvidia.com catalogue when checked. Verify hosted availability before you plan around it.

Trying it against Whisper

Benchmark it head to head with Whisper Large v3 Turbo on twenty of your longest, messiest files. Score WER, then score diarisation separately with cpWER or a manual check of speaker turns. Timestamp drift at the end of an hour-long file is the thing to look at closely.

More in automatic speech recognition and on NVIDIA's provider page.

How to evaluate Nemotron 3.5 Transcribe 30B A4B

Compare the model on the work you need to complete.

Tasks and inputs

Nemotron 3.5 Transcribe 30B A4B is listed for Automatic speech recognition, Translation, Speaker Diarization. It accepts audio and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Documented limits: 65.54K context. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under OpenMDW-1.1. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

Up to about one hour of 16 kHz mono audio in a single request. It is an offline model, not a streaming one.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

salesforce

SOV-Transcribe-1

SOV-Transcribe-1 is Salesforce's open-weight speech-augmented model for non-streaming transcription, with keyword biasing and style instructions; Apache-2.0.

— context

ElevenLabs

Scribe v3 Live

Scribe v3 Live is ElevenLabs' streaming transcription model with turn prediction, mid-sentence language switching and a 10,000-term keyterm library.

— context

IBM

Granite Speech 5.0 2B

Granite Speech 5.0 2B is IBM's open speech-language model for multilingual ASR and translation with keyword biasing, runnable from Ollama to MLX.

— context

Mistral AI

Voxtral Mini Transcribe 3

Voxtral Mini Transcribe 3 is Mistral's 4B batch transcription model with speaker labels, segment timestamps and custom vocabulary, replacing Mini 2.

65.54K context

Mistral AI

Voxtral Mini Transcribe Realtime 3

Voxtral Mini Transcribe Realtime 3 is Mistral's streaming speech-to-text model for voice agents: under 500 ms, tunable delay, built-in turn detection.

— context

Mistral AI

Voxtral Small Transcribe 3

Voxtral Small Transcribe 3 is Mistral's top-accuracy batch speech-to-text model for recorded audio, with context biasing and 50+ languages.

— context