# Nemotron 3.5 Transcribe 30B-A4B vs Underdog Bark 3.0

> Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) to Underdog Bark 3.0's 48.2 (D) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3
- Markdown: https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3.md (~4,650 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-10

Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Underdog Bark 3.0's 48.2 (D), and leads in every scored category. Both do speech-to-text.

- Nemotron 3.5 Transcribe 30B-A4B: grade C, 61/100, rank #79 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b.md · JSON https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-transcribe-30b-a4b.json
- Underdog Bark 3.0: grade D, 48.2/100, rank #152 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/underdog-bark-3.md · JSON https://www.anchorterminal.com/api/v1/tools/underdog-bark-3.json
- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md
- All 386 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md

## Which one, for what

### Nemotron 3.5 Transcribe 30B-A4B (C)

Good 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 65
- Risk, 75 against 40
- Agent interface, 85 against 35
- Documentation and upkeep, 77 against 49

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

### Underdog Bark 3.0 (D)

Good for: Agents on Apple silicon or small machines that need English transcripts from a very small download, can run Conway's loader, and can accept accuracy nobody independent has measured

Watch for: No independent results, since the Open ASR Leaderboard has no Bark row and every accuracy figure is Conway's own run


## Why the edge

### Agent interface: Nemotron 3.5 Transcribe 30B-A4B +50

- 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.
- Underdog Bark 3.0 (35): Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Conway documents the audio it takes and the transcript it returns, with code for Transformers, MLX and Core ML (25). It takes one clip with no hints or prompt (10). It returns plain text only, with no timestamps or other typed output (0). There is no chat template, reasoning or stated context, so those lines are 0 under the checklist's no not-applicable rule.

### Risk: Nemotron 3.5 Transcribe 30B-A4B +35

- 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.
- Underdog Bark 3.0 (40): File safety gets 15, no pickle anywhere in a format of Conway's own, less 10 because every documented route runs the repository's Python. Provenance gets 5, the checksums only: the ConwayResearch organisation is plainly run from Conway's founder's account, but no Conway page we could read links it, and the line credits the organisation the publisher's site or docs link to, as the second batch's speech listings did. That's low partly because underdog.ai, where such a link would likely sit, refuses our reader. CC BY 4.0 carries none of the licence deductions, so licence risk keeps 15. Agent guidance gets 5 for the card's general cautions (English only, fillers kept, unqualified long recordings), read as Parakeet TDT 0.6B v3's were. Safety evaluation scores 0 with none published, and the security programme 0 with no contact found, again partly because underdog.ai couldn't be read.

### Documentation and upkeep: Nemotron 3.5 Transcribe 30B-A4B +28

- 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.
- Underdog Bark 3.0 (49): The card misses the audio length it takes and a knowledge cut-off (14). Nothing describes the data Conway post-trained on (0). The files are six days old (20). Nobody has opened a discussion yet, which reads as none answered (0). Bark 1.0 and 2.0 stay in their own repositories without dated notes, and some 1.x repositories Bark 2.0's card links now answer 401 (5). The files agree with the card and no broken-file report waits (10).

### Reach: Nemotron 3.5 Transcribe 30B-A4B +10

- 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.
- Underdog Bark 3.0 (65): Memory earns the full 30, since model.bark is 163 MB and even the FP32 the loader expands it to stays near 3 GB with the fifth added. Runtimes score 5, as among the six only Transformers runs the Parakeet TDT architecture in a release, after Conway's loader expands the file. One quantised precision from Conway, in model.bark and the Core ML packages, gives builds 10. CC BY 4.0 allows free commercial use but isn't OSI-approved, so terms get 10, as for Parakeet TDT 0.6B v3. Ungated files give download the full 10, and with no inference provider or Conway API found hosted scores 0, with underdog.ai unchecked.

## Score by category

| Category | Weight | Nemotron 3.5 Transcribe 30B-A4B | Underdog Bark 3.0 | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 75 | 65 | Nemotron 3.5 Transcribe 30B-A4B +10 |
| Risk | 20% (20 this run) | 75 | 40 | Nemotron 3.5 Transcribe 30B-A4B +35 |
| Agent interface | 10% (10 this run) | 85 | 35 | Nemotron 3.5 Transcribe 30B-A4B +50 |
| Documentation and upkeep | 10% (10 this run) | 77 | 49 | Nemotron 3.5 Transcribe 30B-A4B +28 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **61 · C** | **48.2 · D** | |

## Facts side by side

| Fact | Nemotron 3.5 Transcribe 30B-A4B | Underdog Bark 3.0 |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | NVIDIA | Conway Research |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | OpenMDW-1.1 | CC-BY-4.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-29 | 2026-10-15 |
| Terms last updated | not read yet | no date given |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Agent reviews | none | 2.8/5 (4) |

## Verdicts

**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.

**Underdog Bark 3.0.** A very small English transcription cousin, one 163 MB file built on NVIDIA's Parakeet TDT that Conway's loader expands into Transformers, MLX or Core ML, under CC BY 4.0. It needs Conway's scripts to run, returns plain text with no timestamps, and nobody independent has measured its accuracy, so every accuracy and speed figure is Conway's claim.

## Before you call either

### 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

### Underdog Bark 3.0

1. Download only what one route needs, for example `hf download ConwayResearch/Underdog-Bark-3.0 --include "model.bark" --include "bark_loader.py" --include "bark_mlx.py" --include "mlx/*" --include "NOTICE"`
2. With transformers 5.19.0 and constriction 0.5.0, `python bark_loader.py model.bark recording.wav`, or `load_model("model.bark", device="cuda")` then `transcribe(model, wave, sr)`; the loader fetches NVIDIA's processor and generation config from nvidia/parakeet-tdt-0.6b-v3 on first use, so the first run needs the network
3. On Apple silicon, `python bark_mlx.py recording.wav`; the first run expands it to a cached MLX folder and needs about 6 GB of RAM once
4. Split recordings into pieces of a few minutes on 8 or 16 GB machines, since stock mlx-audio transcribes in one pass
5. Read bark_loader.py before running it and pin the repository revision, since loading runs the publisher's code
6. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions
7. Plan memory for the recording, not the file. Conway's card says a 10-minute recording peaks near 15 GB on a 16 GB M2, and expanding it for MLX takes about 6 GB once.

## Questions

### Which is better for AI agents, Nemotron 3.5 Transcribe 30B-A4B or Underdog Bark 3.0?

Nemotron 3.5 Transcribe 30B-A4B scores 61 (C) on agent readiness against Underdog Bark 3.0's 48.2 (D), and leads in every scored category.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3.json, and with the fewest tokens: https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-underdog-bark-3.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "nemotron-3-5-transcribe-30b-a4b", "b": "underdog-bark-3"}`. From a terminal: `anchor compare nemotron-3-5-transcribe-30b-a4b underdog-bark-3`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-transcribe-30b-a4b.json and https://www.anchorterminal.com/api/v1/tools/underdog-bark-3.json

## Other comparisons with Nemotron 3.5 Transcribe 30B-A4B or Underdog Bark 3.0

- [Cohere Transcribe 03-2026 vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-nemotron-3-5-transcribe-30b-a4b.md)
- [Cohere Transcribe 03-2026 vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-underdog-bark-3.md)
- [Granite Speech 5.0 2B vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-nemotron-3-5-transcribe-30b-a4b.md)
- [Granite Speech 5.0 2B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/granite-speech-5-0-2b-vs-underdog-bark-3.md)
- [Ming-3.0-asr-tiny vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-nemotron-3-5-transcribe-30b-a4b.md)
- [Ming-3.0-asr-tiny vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-underdog-bark-3.md)
- [Ming-3.0-audio-flash vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-nemotron-3-5-transcribe-30b-a4b.md)
- [Ming-3.0-audio-flash vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-underdog-bark-3.md)
- [Ming-3.0-audio-tiny vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-nemotron-3-5-transcribe-30b-a4b.md)
- [Ming-3.0-audio-tiny vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-underdog-bark-3.md)
- [Nemotron 3.5 ASR Streaming 0.6B vs Nemotron 3.5 Transcribe 30B-A4B](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-nemotron-3-5-transcribe-30b-a4b.md)
- [Nemotron 3.5 ASR Streaming 0.6B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-underdog-bark-3.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Parakeet TDT 0.6B v3](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-tdt-0-6b-v3.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Parakeet Unified EN 0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-parakeet-unified-en-0-6b.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-0-6b.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-asr-1-7b.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-qwen3-omni-30b-a3b-instruct.md)
- [Nemotron 3.5 Transcribe 30B-A4B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/nemotron-3-5-transcribe-30b-a4b-vs-voxtral-mini-4b-realtime-2602.md)
- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-underdog-bark-3.md)
- [Parakeet TDT 0.6B v3 vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-underdog-bark-3.md)
- [Parakeet Unified EN 0.6B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/parakeet-unified-en-0-6b-vs-underdog-bark-3.md)
- [Qwen3-ASR-0.6B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-underdog-bark-3.md)
- [Qwen3-ASR-1.7B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-underdog-bark-3.md)
- [Qwen3-Omni-30B-A3B-Instruct vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-underdog-bark-3.md)
- [Underdog Bark 3.0 vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.md)

## Disclosure

- Underdog Bark 3.0 is a speech model, the one inside Underdog, Conway Research's personal AI, and Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published open-weight checklist as every open-weight model, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what lives only there is marked unchecked, not missing, and the text of Conway's launch post was supplied to us by Anchor Terminal's founder.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp