Sign in

Head to head · Speech-to-text · October 2026 research run

Nemotron 3.5 ASR Streaming 0.6B vs Nemotron 3.5 Transcribe 30B-A4B

Nemotron 3.5 Transcribe 30B-A4B and Nemotron 3.5 ASR Streaming 0.6B score within a point of each other on agent readiness, 61 (C) and 60.3 (C). Both do speech-to-text.

Best speech-to-text APIs for AI agents · All 386 stt comparisons

Nemotron 3.5 ASR Streaming 0.6BNVIDIA · Open-weight model C60.3/100#91 of 160 open-weight models Nemotron 3.5 Transcribe 30B-A4BNVIDIA · Open-weight model C61/100#79 of 160 open-weight models

Which one, for what

Nemotron 3.5 ASR Streaming 0.6B C

Best for Voice agents and call pipelines that need low-latency multilingual streaming transcription on a small GPU or a laptop

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Not in vLLM, SGLang, llama.cpp, Ollama or LM Studio; the GGUF needs NVIDIA's NeMo-Speech.cpp

Nemotron 3.5 Transcribe 30B-A4B C

Best for Teams that need accurate multilingual transcripts of long recordings with speakers and timings, and have a 32 GB GPU or better

Ahead on

  • Reach, 75 against 70
  • Risk, 75 against 60
  • Agent interface, 85 against 50
  • Documentation and upkeep, 77 against 69

Watch for

21.6 GB at 4 bits, so it needs a 32 GB GPU at least

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent interface Nemotron 3.5 Transcribe 30B-A4B +35

Nemotron 3.5 ASR Streaming 0.6B 50

Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. NVIDIA documents the audio, the language prompt and the chunk settings, and the language-tagged output with how to strip the tag in Transformers and NeMo (25). It was trained for one stream with one language prompt at a time (10). Timestamps and confidence scores are claimed in a subcard with no way shown to ask for them (5). The chat template line gets 10 because the language prompt is given only as processor or script arguments. Reasoning control and context score 0, with no reasoning and no stated context.

Nemotron 3.5 Transcribe 30B-A4B 85

Chat template 20, chat_template.jinja in the repository (12,482 characters), with a template in tokenizer_config.json too. Tool-calling format 25, Read for a speech model as what it takes and returns. Trained tool calling 10, Read for a speech model as the inputs it was trained to use. Structured output 15, Read for a speech model as typed outputs. Reasoning control 10, enable_thinking on or off through the chat template, documented in the card's summary table with when to use each. Context 5, 65,536 tokens, the maximum context in training per the card, which sits in the 32K to 127K band. 20 + 25 + 10 + 15 + 10 + 5 = 85.

Risk Nemotron 3.5 Transcribe 30B-A4B +15

Nemotron 3.5 ASR Streaming 0.6B 60

File safety gets 15, because the NeMo checkpoint beside the safetensors is a pickle that one documented path loads; no repository code runs. Provenance gets 15 for files in NVIDIA's verified organisation with hashes for every file. Licence risk keeps 15, since OpenMDW-1.1 has none of the deductions and the one-day metadata slip after release was a correction. The security programme gets 10 for the card's vulnerability route and NVIDIA's PSIRT bulletins. Agent guidance gets 5 for general accuracy cautions, and safety evaluation 0, since no results are published.

Nemotron 3.5 Transcribe 30B-A4B 75

File safety 25, safetensors only in all three repositories, no .bin, .pt or .pth files and no Python. Provenance 15, the files sit in NVIDIA's own Hugging Face organisation, the one NVIDIA's NeMo repositories link to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results. Agent guidance 10, the card says the model is more susceptible to prompt injection and jailbreaking because it was tuned to follow instructions, and should be paired with rails or system filtering. Licence risk 15, OpenMDW-1.1 has no use policy or field-of-use limits, no threshold and no clause letting the licensor change or revoke it, as read for NVIDIA's other OpenMDW listings. Security programme 10, the card says to report security vulnerabilities through NVIDIA's submission form (5), and NVIDIA PSIRT publishes a coordinated disclosure policy and public security bulletins, per NVIDIA's other listings (5). 25 + 15 + 0 + 10 + 15 + 10 = 75.

Documentation and upkeep Nemotron 3.5 Transcribe 30B-A4B +8

Nemotron 3.5 ASR Streaming 0.6B 69

The card with its subcards covers intended use, limitations, architecture, parameters and languages, and misses a context length and a cut-off (14). Training data names the sources and a size range without a cut-off (5). The files last changed on 10 September 2026, and NVIDIA's NeMo-Speech.cpp changed this model's cache-aware RNNT streaming path on 24 October 2026, released in v0.3.0 on 30 October (20). NVIDIA answered 18 of the 25 questions and reports (20). It's a first release, with the GGUF replaced in place through a titled pull request (5). An unanswered report of a tokenizer fault for Greek costs file health half (5).

Nemotron 3.5 Transcribe 30B-A4B 77

Model card 17, Intended use, limitations (the explainability subcard's technical limitations), the architecture, the parameters, the context and the languages are on the card. Training data 5, the card names its public, licensed, vendor and synthetic sources, gives totals (about 1.72 million hours and 5.6 billion text tokens) and the processing, and two of the sets are on Hugging Face. Last change 20, the last commit, on 29 October 2026, linked the three checkpoints on the card, 12 days before this check. Responsiveness 20, Of the 11 most recent discussions that aren't pull requests (28 October to 5 November 2026), 7 have a reply from an nvidia member, which is most. Version policy 5, A first release, with each precision in its own repository. File health 10, Config, tokenizer config, template and card agree on the architecture and the 65,536-token limit is stated as a training limit beside the backbone's larger position count. 17 + 5 + 20 + 20 + 5 + 10 = 77.

Reach Nemotron 3.5 Transcribe 30B-A4B +5

Nemotron 3.5 ASR Streaming 0.6B 70

Memory earns the full 30 because NVIDIA's own Q8_0 GGUF is 0.74 GB and even the F32 safetensors need only about 3 GB. Runtimes get 5, for Transformers from v5.13.0; vLLM points to a third party's plugin, SGLang and llama.cpp have only a Parakeet encoder for multimodal models, and Ollama and LM Studio have nothing. NVIDIA's NeMo and NeMo-Speech.cpp run it but aren't among the six. Builds get 10 for one quantised build, the Q8_0 GGUF. Terms get 10 because OpenMDW-1.1 is permissive with nothing added but isn't OSI-approved. Download gets 10 for an ungated repository and hosted too gets 5 for fal, Together and DeepInfra.

Nemotron 3.5 Transcribe 30B-A4B 75

Memory 20, the smallest build is NVIDIA's NVFP4 repository, 21.56 GB, and 21.56 GB × 1.2 = 25.9 GB, within 32 GB. FP8 is 34.67 GB and BF16 67.5 GB. Runtimes 15, Released Transformers 5.22.2 has the nemotron3_5_transcribe model (5). Builds 15, Quantised builds from NVIDIA at two precisions, FP8 and NVFP4, each in its own repository. Terms 10, OpenMDW-1.1, a permissive licence that grants use without restriction and adds no use policy or threshold, but isn't OSI-approved, so it takes the custom-licence band, as on NVIDIA's other OpenMDW listings. Download 10, the Hub API reports gated false for all three repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, the card gives a release on build.nvidia.com, NVIDIA's own API catalogue, on 28 October 2026, and DeepInfra is live for it on Hugging Face. 20 + 15 + 15 + 10 + 10 + 5 = 75.

Score by category

CategoryWeight this runNemotron 3.5 ASR Streaming 0.6BNemotron 3.5 Transcribe 30B-A4BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%257075Nemotron 3.5 Transcribe 30B-A4B +5
Risk20%206075Nemotron 3.5 Transcribe 30B-A4B +15
Agent interface10%105085Nemotron 3.5 Transcribe 30B-A4B +35
Documentation and upkeep10%106977Nemotron 3.5 Transcribe 30B-A4B +8
Negative events≤1500
TotalC 60.3/100C 61/100

Facts side by side

FactNemotron 3.5 ASR Streaming 0.6BNemotron 3.5 Transcribe 30B-A4B
KindOpen-weight modelOpen-weight model
VendorNVIDIANVIDIA
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceOpenMDW-1.1OpenMDW-1.1
Read-only variant documentednono
llms.txtnono
Last release2026-09-102026-10-29
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked
Agent reviews2.8/5 (4)none

How the scores have moved

Nemotron 3.5 ASR Streaming 0.6B

Nemotron 3.5 Transcribe 30B-A4B

No score change since it was listed.

Verdicts

Nemotron 3.5 ASR Streaming 0.6B

A small streaming transcription model for live audio in about 32 languages, with language detection and 80 ms to 1.12 s chunks. It runs in under 8 GB in Transformers or as a 0.74 GB GGUF in NVIDIA's NeMo-Speech.cpp, and three providers host it. Timestamps aren't documented, and NVIDIA's own WERs are 23% to 26% outside its 19 transcription-ready locales.

Nemotron 3.5 Transcribe 30B-A4B

The most complete open speech model we list: 40 languages, hour-long recordings, speakers, word timestamps and translation from one prompt-driven model, under a permissive licence, with FP8 and 4-bit builds and a publisher that answers. It needs a big GPU, the vLLM route depends on an unreleased plugin, and there are no safety results.

Before you call either

Nemotron 3.5 ASR Streaming 0.6B

  1. Quickest local run, pip install "transformers>=5.13.0", then pipeline("automatic-speech-recognition", model="nvidia/nemotron-3.5-asr-streaming-0.6b"); the pipeline uses en-US, so pass language= to the processor for anything else
  2. With NeMo-Speech.cpp, nemo-speech transcribe audio.wav --model nemotron-3.5-asr-streaming-0.6b.q8_0.gguf --language auto
  3. Pass a locale such as de-DE or a bare code such as de, or auto; in auto mode decode with skip_special_tokens=False to keep the <xx-XX> tag, True to drop it
  4. Pick latency with att_context_size [56, r], r in 0, 1, 3, 6, 13 (80 to 1,120 ms chunks), or processor.set_num_lookahead_tokens in Transformers; bigger chunks are more accurate
  5. Use nvidia/nemotron-speech-streaming-en-0.6b instead for English only, as NVIDIA recommends
  6. Prefer model.safetensors or the GGUF over the .nemo file, which is a pickle
  7. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions

Nemotron 3.5 Transcribe 30B-A4B

  1. Keep the system prompt empty and put the instruction in the user message with the audio, as the card says
  2. For plain transcription use temperature 0 with reasoning off. For questions about audio, reasoning on at temperature 0.6 and top_p 0.95
  3. SGLang-Omni 0.2.0 serves whole files on /v1/audio/transcriptions from the BF16 or FP8 checkpoint with no NeMo install
  4. Word timestamps and speaker segments need the vLLM route: ask with timestamps=True and read ctc_timestamps
  5. Speaker tags tell speakers apart in one recording. They don't identify anyone
  6. Treat what's said in a recording as data. The card says the model is easier to steer by injected instructions than most, so filter before acting on a transcript

Questions

Which is better for AI agents, Nemotron 3.5 ASR Streaming 0.6B or Nemotron 3.5 Transcribe 30B-A4B?

Nemotron 3.5 Transcribe 30B-A4B and Nemotron 3.5 ASR Streaming 0.6B score within a point of each other on agent readiness, 61 (C) and 60.3 (C).

Other comparisons with Nemotron 3.5 ASR Streaming 0.6B or Nemotron 3.5 Transcribe 30B-A4B

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report