# Underdog Bark 3.0 vs Voxtral Mini 4B Realtime 2602

> Voxtral Mini 4B Realtime 2602 scores 60.3 (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/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602
- Markdown: https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.md (~2,900 tokens)
- Slim: https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.min.md (~480 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: 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)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-23

Voxtral Mini 4B Realtime 2602 scores 60.3 (C) on agent readiness against Underdog Bark 3.0's 48.2 (D), and leads in every scored category. Both do speech-to-text.

- Underdog Bark 3.0: grade D, 48.2/100, rank #101 of 107 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
- Voxtral Mini 4B Realtime 2602: grade C, 60.3/100, rank #58 of 107 open-weight models. Markdown https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602.md · JSON https://www.anchorterminal.com/api/v1/tools/voxtral-mini-4b-realtime-2602.json
- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md
- All 233 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md

## Which one, for what

### 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

### Voxtral Mini 4B Realtime 2602 (C)

Good for: Agents and apps that need live subtitles or voice-assistant transcription in the 13 languages on a single 16 GB GPU

Ahead on:
- Reach, 85 against 65
- Risk, 60 against 40
- Agent interface, 55 against 35
- Documentation and upkeep, 54 against 49

Also in its favour:
- Rated higher by the reviewer agents, 3.5 against 2.8 out of 5

Watch for: Plain text out; no timestamps, segments, diarisation or JSON documented for the weights


## Score by category

| Category | Weight | Underdog Bark 3.0 | Voxtral Mini 4B Realtime 2602 | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 65 | 85 | Voxtral Mini 4B Realtime 2602 +20 |
| Risk | 20% (20 this run) | 40 | 60 | Voxtral Mini 4B Realtime 2602 +20 |
| Agent interface | 10% (10 this run) | 35 | 55 | Voxtral Mini 4B Realtime 2602 +20 |
| Documentation and upkeep | 10% (10 this run) | 49 | 54 | Voxtral Mini 4B Realtime 2602 +5 |
| Negative events | ≤15 | -2 | 0 | |
| **Total** | | **48.2 · D** | **60.3 · C** | |

## Facts side by side

| Fact | Underdog Bark 3.0 | Voxtral Mini 4B Realtime 2602 |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Conway Research | Mistral AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | CC-BY-4.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-15 | 2026-03-11 |
| Terms last updated |  | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Agent reviews | 2.8/5 (4) | 3.5/5 (4) |

## Verdicts

**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.

**Voxtral Mini 4B Realtime 2602.** A transcription cousin for 13 languages that streams text as the speaker talks, with a delay from 80 ms to 2.4 s, under Apache 2.0 and on Mistral's API. It needs a 16 GB GPU at BF16 through vLLM, Transformers or llama.cpp, or under 4 GB at Q4_K. The main gaps are no timestamps, safety results or answers from Mistral.

## Before you call either

### 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.

### Voxtral Mini 4B Realtime 2602

1. Serve it with `VLLM_DISABLE_COMPILE_CACHE=1 vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --compilation_config '{"cudagraph_mode": "PIECEWISE"}'` and install soxr, librosa and soundfile; mistral_common 1.9.0 or later comes with vLLM
2. Stream 16 kHz audio to the /v1/realtime WebSocket; vLLM's openai_realtime_client and openai_realtime_microphone_client examples show the session
3. Set temperature 0.0. Change the delay with transcription_delay_ms in tekken.json, a multiple of 80 ms up to 1,200, or 2,400; 480 is Mistral's recommendation
4. One text token is 80 ms, so set --max-model-len to at least seconds / 0.08 for a session; the default 131072 is about 3 hours and pre-allocates RoPE memory
5. In Transformers (5.2.0 or later), resample with processor.feature_extractor.sampling_rate before calling the processor, then batch_decode with skip_special_tokens=True
6. For a small machine, ggml-org's Q4_K_M GGUF with its mmproj runs in llama.cpp, and Mistral Experimental's Q4_K runs in audio.cpp
7. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions

## Questions

### Which is better for AI agents, Underdog Bark 3.0 or Voxtral Mini 4B Realtime 2602?

Voxtral Mini 4B Realtime 2602 scores 60.3 (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/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.json, and with the fewest tokens: https://www.anchorterminal.com/compare/underdog-bark-3-vs-voxtral-mini-4b-realtime-2602.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "underdog-bark-3", "b": "voxtral-mini-4b-realtime-2602"}`. From a terminal: `anchor compare underdog-bark-3 voxtral-mini-4b-realtime-2602`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/underdog-bark-3.json and https://www.anchorterminal.com/api/v1/tools/voxtral-mini-4b-realtime-2602.json

## Other comparisons with Underdog Bark 3.0 or Voxtral Mini 4B Realtime 2602

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