Full card: links to Plus, the benchmark, GitHub and the project page; cover loop

413b031 verified 1 day ago

13.3 kB

---
language:
- en
- multilingual
tags:
- audio
- speech
- antispoofing
- deepfake-detection
- source-tracing
- audio-language-model
license: cc-by-nc-4.0
pipeline_tag: audio-text-to-text
base_model:
- openbmb/MiniCPM5-2B
- Qwen/Qwen3-ASR-1.7B
datasets:
- mueller91/MLAAD
- jungjee/spoofceleb
- CodecFake/CodecFake_Plus_Dataset
- isjwdu/DFADD
---
<div align="center">

# VeriSpoof-Base

**Beyond real or fake: one unified audio LLM for speech deepfake forensics.**

[![arXiv](https://img.shields.io/badge/arXiv-2611.04634-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2611.04634)
[![Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Space-FFD21E)](https://huggingface.co/spaces/AustinXiao/VeriSpoof-demo)
[![Project Page](https://img.shields.io/badge/Project-Page-000F46)](https://swagshaw.github.io/verispoof/)
[![GitHub](https://img.shields.io/badge/GitHub-Code-181717?logo=github)](https://github.com/swagshaw/verispoof)
[![Benchmark](https://img.shields.io/badge/%F0%9F%A4%97%20Benchmark-VeriSpoof--Bench-FFD21E)](https://huggingface.co/datasets/AustinXiao/VeriSpoof-Bench)
[![License](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey)](https://creativecommons.org/licenses/by-nc/4.0/)

[![Speech-DF-Arena](https://img.shields.io/badge/%F0%9F%A5%88%20Speech--DF--Arena-%232%20open--weight%20%C2%B7%204.43%25%20EER-A7A9AC)](https://huggingface.co/spaces/Speech-Arena-2025/Speech-DF-Arena)
[![SpoofRadar](https://img.shields.io/badge/%F0%9F%A5%88%20SpoofRadar%20v1.0-%232%20open--weight%20%C2%B7%204.23%25%20EER-A7A9AC)](https://tefficlabs.com/spoofradar)
[![VeriSpoof-Plus](https://img.shields.io/badge/New-%F0%9F%A5%87%20VeriSpoof--Plus%20%C2%B7%20%231%20open--weight-E8452C)](https://huggingface.co/AustinXiao/VeriSpoof-Plus)

</div>

<a href="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/verispoof_cover.mp4"><img src="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/verispoof_cover.gif" alt="VeriSpoof in 12 seconds: it hears the synthesized word and answers every forensic question with one model" width="100%"></a>

**VeriSpoof-Base** is an open-weight audio language model for speech deepfake forensics, trained on the official
training splits of public corpora only. From a single recording it decides whether the speech is genuine or spoofed, names the system that generated it,
tells whether a second recording comes from the same generator, acoustic model or vocoder, and recognizes the noise,
reverberation and codec of the channel. It explains every decision in short lines that can each be checked against
the audio, and its 2.9 B parameters run on a single 12 GB GPU.

It ranks #4 of 28 systems on [Speech-DF-Arena](https://huggingface.co/spaces/Speech-Arena-2025/Speech-DF-Arena) (4.43%
pooled EER over 14 test sets), ahead of every open-weight system other than
[VeriSpoof-Plus](https://huggingface.co/AustinXiao/VeriSpoof-Plus), and is the model of all controlled studies in the
[technical report](https://arxiv.org/abs/2611.04634).

![VeriSpoof-Base: one model answers five forensic questions; fourth of 28 systems and second among open-weight ones, after VeriSpoof-Plus, on Speech-DF-Arena](assets/overview.png)

## News

- **2026-11-04** · 🥇 New: **[VeriSpoof-Plus](https://huggingface.co/AustinXiao/VeriSpoof-Plus)**, #1 open-weight on
  Speech-DF-Arena (pooled EER 2.14%, #3 of 28 systems) and on SpoofRadar v1.0 (4.04%).
- **2026-11-04** · 🥈🏆 **#2 open-weight on SpoofRadar v1.0**: pooled EER 4.23% over 16 test sets, behind only
  VeriSpoof-Plus; the next open-weight system is at 9.96%.
- **2026-10-31** · 🥈🏆 **#2 open-weight on Speech-DF-Arena**: pooled EER 4.43% over 14 test sets, #4 of 28 systems,
  behind only VeriSpoof-Plus; the next open-weight system is at 9.52% (public snapshot of 31 Oct 2026).
- **2026-10-31** · VeriSpoof-Base released.

## Highlights

- **Strong detection on official training splits only.** Fourth of 28 systems on Speech-DF-Arena (4.43% pooled EER)
  and 4.23% pooled EER on SpoofRadar v1.0, ahead of every open-weight system other than VeriSpoof-Plus
  on both boards. It is the model of
  all controlled studies in the [technical report](https://arxiv.org/abs/2611.04634).
- **One model, five forensic questions.** The same weights detect spoofed speech, identify the generator (95.4% on
  MLAAD), name the acoustic model under an unseen vocoder (84.7%), verify whether two recordings come from the same
  system, and recognize noise, reverberation and codec. Every answer is the model's own text answer, scored; there are
  no task-specific heads.
- **Evidence you can check.** The reasoning states bandwidth, noise level, the synthesized span and a decision, each
  line checkable against the audio. The decision follows the evidence: invert the stated span and the decision flips,
  in 100% of tests and in 99.5% with wording never seen in training.
- **Catches partial fakes.** With reasoning, 99.6% of partially edited recordings in PartialEdit are caught, against
  78.4% for the one-step answer.

Need the best numbers? See [Base or Plus?](https://huggingface.co/AustinXiao/VeriSpoof-Plus#base-or-plus)

## The film

<video controls preload="metadata" poster="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/film_poster.jpg" src="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/verispoof_film.mp4" width="100%"></video>

*1:59, Chinese and English captions. All voices in the film are synthetic (Fish Audio), including Yang Xiao’s. Music “78 PULSE” by kjartan_abel (CC BY 4.0); sound effects “2 Impact Wet” by original_sound (CC BY 3.0) and “data corrupted” by Saltbearer (CC BY 4.0), the rest CC0, via Openverse and Freesound; recordings from PartialEdit (CC BY 4.0) and MLAAD (CC BY-NC 4.0). Every model output shown is a real VeriSpoof output on that clip. The character is AI-generated art.*

## Model at a glance

| | |
|---|---|
| Parameters | 2.9 B: audio encoder from Qwen3-ASR-1.7B, language model MiniCPM5-2B |
| Input | a speech recording at any sample rate (resampled to 16 kHz) |
| Output | an answer with its score; reasoning lines; a per-token synthetic-speech probability (every 0.16 s) |
| Tasks | detection, generator identification, source verification, recording condition, grounded reasoning |
| Hardware | one CUDA GPU with about 12 GB |

## Quick start

```bash
hf download AustinXiao/VeriSpoof-Base --include "code/*" --local-dir verispoof
pip install ./verispoof/code
```

```python
from verispoof import VeriSpoof
model = VeriSpoof.from_pretrained("AustinXiao/VeriSpoof-Base")   # weights are downloaded on first use
# Detection. score = log p(spoof answer) - log p(bona fide answer); label uses threshold 0
model.detect("sample.wav")                        # {'label': 'spoof', 'score': ...}
model.detect(["a.wav", "b.flac"], batch_size=16)  # a list in, a list out; arrays need sr=...
# Grounded reasoning, plus the per-token head (probability that each 0.16 s token is synthesized)
r = model.explain("sample.wav")
print(r["text"])         # OBSERVATIONS / CHANNEL_STATUS / LOCALIZATION / SOURCE_PROFILE / DECISION lines
r["decision"], r["spans"], r["token_prob"]
# Source verification of two spoofed recordings: generator, acoustic_model or vocoder
model.same_source("a.wav", "b.wav", level="generator")   # {'same': ..., 'score': log p(yes) - log p(no)}
model.compare("a.wav", "b.wav")                           # source-verification reasoning
# Closed questions
model.condition("sample.wav", attr="codec")               # also "noise", "reverb"
model.generator("sample.wav", ["XTTS-v2", "Bark", "VITS"])  # candidate systems you supply
```

### Faster reasoning with vLLM

```bash
pip install "./verispoof/code[vllm]"
```

```python
from verispoof.vllm_backend import VeriSpoofVLLM
if __name__ == "__main__":          # vLLM starts its engine in a separate process
    m = VeriSpoofVLLM.from_pretrained("AustinXiao/VeriSpoof-Base")
    results = m.explain(["a.wav", "b.wav", "c.wav"])   # batched
    pairs = m.compare([("a.wav", "b.wav"), ("c.wav", "d.wav")])
```

| Reasoning, one A100 | per recording | speed-up |
|---|---:|---:|
| `VeriSpoof.explain`, one at a time | 2.24 s | 1× |
| `VeriSpoofVLLM.explain`, one at a time | 0.50 s | 4.5× |
| `VeriSpoofVLLM.explain`, batch of 64 | 0.05 s | 46× |

Decisions are identical to `VeriSpoof` (64 / 64 recordings, 32 / 32 pairs). Detection scores and the per-token head
use `VeriSpoof`. If vLLM fails to load a FlashInfer sampling kernel, set `VLLM_USE_FLASHINFER_SAMPLER=0`.

## Results

### Speech-DF-Arena leaderboard

Public snapshot of 31 Oct 2026, ordered by pooled EER as on the board; every line of the official protocols
([speech_df_arena](https://github.com/Speech-Arena/speech_df_arena), commit 97a4445) is scored.

| System | Availability | Params | Average EER | Pooled EER |
|---|---|---:|---:|---:|
| Modulate VELMA-2 | Proprietary | 0.3 B | 1.10 | 1.59 |
| Resemble Detect-3B-Omni | Proprietary | 3 B | 2.60 | 2.10 |
| 🥇 VeriSpoof-Plus | Open-weight | 2.9 B | 1.79 | 2.14 |
| Hiya Authenticity Verification | Proprietary | 1 B | 2.11 | 2.32 |
| 🥈 **VeriSpoof-Base (this model)** | **Open-weight** | **2.9 B** | **4.28** | **4.43** |
| DLMSL SpeakSure | Proprietary | 0.7 B | 3.80 | 6.14 |
| Whispeak | Proprietary | 0.1 B | 3.05 | 8.06 |
| DF Arena 1B | Open-weight | 1 B | 5.66 | 9.52 |
| XLS-R + SLS | Open-weight | 0.3 B | 14.01 | 16.08 |

Average = mean of the 14 set EERs. Each VeriSpoof model is ranked on its own (Plus third of 28, Base fourth of 28).

<details>
<summary>Per test set</summary>

| Dataset | Trials | EER (%) | Accuracy (%) |
|---|---:|---:|---:|
| asvspoof_2019 | 71,237 | 0.49 | 99.25 |
| asvspoof_2021_la | 148,176 | 5.48 | 93.54 |
| asvspoof_2021_df | 533,928 | 0.97 | 99.40 |
| asvspoof_2024 | 680,774 | 2.59 | 98.42 |
| in_the_wild | 31,779 | 1.20 | 98.93 |
| fake_or_real | 4,528 | 5.39 | 90.02 |
| codecfake | 304,241 | 4.97 | 89.51 |
| add_2022_track_1 | 109,199 | 14.05 | 88.42 |
| add_2022_track_3 | 126,861 | 3.87 | 96.84 |
| add_2023_round_1 | 111,976 | 5.01 | 90.35 |
| add_2023_round_2 | 118,477 | 10.61 | 92.87 |
| dfadd | 3,755 | 0.00 | 99.97 |
| librisevoc | 92,407 | 0.02 | 99.99 |
| sonar | 3,948 | 5.19 | 83.11 |
| **Average** | | **4.28** | 94.33 |
| **Pooled** | 2,341,286 | **4.43** | |

Accuracy at threshold 0.

</details>

### SpoofRadar v1.0 leaderboard

16 test sets; pooled EER, and accuracy and macro-F1 at the pooled-EER threshold, as SpoofRadar defines them. Other
rows from the published leaderboard (v1.0); ours computed with the same protocol files.

| System | Availability | Pooled EER | Accuracy | Macro-F1 | Average EER |
|---|---|---:|---:|---:|---:|
| Teffic-Audio | Commercial | 1.37 | 98.63 | 98.12 | 1.09 |
| WavLM-L (Teffic) | Closed source | 3.65 | 96.35 | 95.06 | 2.88 |
| 🥇 VeriSpoof-Plus | Open-weight | 4.04 | 95.96 | 94.54 | 1.65 |
| 🥈 **VeriSpoof-Base (this model)** | **Open-weight** | **4.23** | **95.77** | **94.29** | **3.76** |
| Whisper (Teffic) | Closed source | 5.75 | 94.25 | 92.33 | 3.94 |
| DF Arena 500M V1 | Open-weight | 9.96 | 90.04 | 87.08 | 5.19 |
| GRL | Open-weight | 13.25 | 86.75 | 83.17 | 9.90 |

### Beyond detection

On [VeriSpoof-Bench](https://huggingface.co/datasets/AustinXiao/VeriSpoof-Bench); details in the tech report.

| Task | Result |
|---|---|
| Detection, SpoofCeleb / CodecFake+ / CodecFake+ CoSG (unseen generators) | EER 0.20 / 3.95 / 4.84% |
| Detection under added noise, reverberation and codecs (6 sets) | mean EER 5.23% |
| Same-generator verification, MLAAD seen / unseen model / unseen architecture | EER 17.23 / 13.80 / 20.25% |
| Same-generator verification, SpoofCeleb / ASVspoof 2019 LA | EER 11.25 / 8.22% |
| Generator identification (MLAAD, closed set) | 95.4% accuracy |
| Acoustic model under an unseen vocoder (SpoofCeleb) | 84.7% accuracy |
| Recording condition (noise / reverberation / codec) | 75.9% accuracy |
| Partial fakes caught after reasoning vs one-step answer (PartialEdit / HAD) | 99.6 vs 78.4 / 99.0 vs 99.0% |
| Decision after reasoning, 11 sets | 91.2–99.6% accuracy |
| Partial-spoof localization, text spans (HAD / PartialEdit / PartialSpoof) | IoU 0.61 / 0.58 / 0.25 |
| Per-token head (HAD / PartialEdit / PartialSpoof) | F1 0.91 / 0.79 / 0.74 |
| Decision follows inverted localization (trained / new wording / inserted span) | 1.00 / 0.995 / 1.00 |
| Source-verification reasoning, verdict EER (SpoofCeleb / STOPA / CoSG / LA19 cond.) | 20.20 / 13.65 / 21.60 / 29.65% |

## Intended use

Research on audio deepfake detection, source tracing and explainable forensics. Not intended as the only basis for
decisions about people; a forensic decision should combine this score with other evidence and human review.

## License

CC BY-NC 4.0 (non-commercial use). The base models keep their Apache-2.0 licences.

## Citation

```bibtex
@misc{verispoof2026,
  title         = {{VeriSpoof}: Beyond Real or Fake with One Audio {LLM}},
  author        = {Xiao, Yang and Dang, Ting},
  year          = {2026},
  eprint        = {2611.04634},
  archivePrefix = {arXiv},
  primaryClass  = {eess.AS},
  url           = {https://arxiv.org/abs/2611.04634}
}
```

## Contact

Yang Xiao, The University of Melbourne, yxiao9550@student.unimelb.edu.au

	---
	language:
	- en
	- multilingual
	tags:
	- audio
	- speech
	- antispoofing
	- deepfake-detection
	- source-tracing
	- audio-language-model
	license: cc-by-nc-4.0
	pipeline_tag: audio-text-to-text
	base_model:
	- openbmb/MiniCPM5-2B
	- Qwen/Qwen3-ASR-1.7B
	datasets:
	- mueller91/MLAAD
	- jungjee/spoofceleb
	- CodecFake/CodecFake_Plus_Dataset
	- isjwdu/DFADD
	---

	<div align="center">

	# VeriSpoof-Base

	Beyond real or fake: one unified audio LLM for speech deepfake forensics.

	[![arXiv](https://img.shields.io/badge/arXiv-2611.04634-B31B1B?logo=arxiv&logoColor=white)](https://arxiv.org/abs/2611.04634)
	[![Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Space-FFD21E)](https://huggingface.co/spaces/AustinXiao/VeriSpoof-demo)
	[![Project Page](https://img.shields.io/badge/Project-Page-000F46)](https://swagshaw.github.io/verispoof/)
	[![GitHub](https://img.shields.io/badge/GitHub-Code-181717?logo=github)](https://github.com/swagshaw/verispoof)
	[![Benchmark](https://img.shields.io/badge/%F0%9F%A4%97%20Benchmark-VeriSpoof--Bench-FFD21E)](https://huggingface.co/datasets/AustinXiao/VeriSpoof-Bench)
	[![License](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey)](https://creativecommons.org/licenses/by-nc/4.0/)

	[![Speech-DF-Arena](https://img.shields.io/badge/%F0%9F%A5%88%20Speech--DF--Arena-%232%20open--weight%20%C2%B7%204.43%25%20EER-A7A9AC)](https://huggingface.co/spaces/Speech-Arena-2025/Speech-DF-Arena)
	[![SpoofRadar](https://img.shields.io/badge/%F0%9F%A5%88%20SpoofRadar%20v1.0-%232%20open--weight%20%C2%B7%204.23%25%20EER-A7A9AC)](https://tefficlabs.com/spoofradar)
	[![VeriSpoof-Plus](https://img.shields.io/badge/New-%F0%9F%A5%87%20VeriSpoof--Plus%20%C2%B7%20%231%20open--weight-E8452C)](https://huggingface.co/AustinXiao/VeriSpoof-Plus)

	</div>

	<a href="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/verispoof_cover.mp4"><img src="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/verispoof_cover.gif" alt="VeriSpoof in 12 seconds: it hears the synthesized word and answers every forensic question with one model" width="100%"></a>

	VeriSpoof-Base is an open-weight audio language model for speech deepfake forensics, trained on the official
	training splits of public corpora only. From a single recording it decides whether the speech is genuine or spoofed, names the system that generated it,
	tells whether a second recording comes from the same generator, acoustic model or vocoder, and recognizes the noise,
	reverberation and codec of the channel. It explains every decision in short lines that can each be checked against
	the audio, and its 2.9 B parameters run on a single 12 GB GPU.

	It ranks #4 of 28 systems on [Speech-DF-Arena](https://huggingface.co/spaces/Speech-Arena-2025/Speech-DF-Arena) (4.43%
	pooled EER over 14 test sets), ahead of every open-weight system other than
	[VeriSpoof-Plus](https://huggingface.co/AustinXiao/VeriSpoof-Plus), and is the model of all controlled studies in the
	[technical report](https://arxiv.org/abs/2611.04634).

	![VeriSpoof-Base: one model answers five forensic questions; fourth of 28 systems and second among open-weight ones, after VeriSpoof-Plus, on Speech-DF-Arena](assets/overview.png)

	## News

	- 2026-11-04 · 🥇 New: [VeriSpoof-Plus](https://huggingface.co/AustinXiao/VeriSpoof-Plus), #1 open-weight on
	Speech-DF-Arena (pooled EER 2.14%, #3 of 28 systems) and on SpoofRadar v1.0 (4.04%).
	- 2026-11-04 · 🥈🏆 #2 open-weight on SpoofRadar v1.0: pooled EER 4.23% over 16 test sets, behind only
	VeriSpoof-Plus; the next open-weight system is at 9.96%.
	- 2026-10-31 · 🥈🏆 #2 open-weight on Speech-DF-Arena: pooled EER 4.43% over 14 test sets, #4 of 28 systems,
	behind only VeriSpoof-Plus; the next open-weight system is at 9.52% (public snapshot of 31 Oct 2026).
	- 2026-10-31 · VeriSpoof-Base released.

	## Highlights

	- Strong detection on official training splits only. Fourth of 28 systems on Speech-DF-Arena (4.43% pooled EER)
	and 4.23% pooled EER on SpoofRadar v1.0, ahead of every open-weight system other than VeriSpoof-Plus
	on both boards. It is the model of
	all controlled studies in the [technical report](https://arxiv.org/abs/2611.04634).
	- One model, five forensic questions. The same weights detect spoofed speech, identify the generator (95.4% on
	MLAAD), name the acoustic model under an unseen vocoder (84.7%), verify whether two recordings come from the same
	system, and recognize noise, reverberation and codec. Every answer is the model's own text answer, scored; there are
	no task-specific heads.
	- Evidence you can check. The reasoning states bandwidth, noise level, the synthesized span and a decision, each
	line checkable against the audio. The decision follows the evidence: invert the stated span and the decision flips,
	in 100% of tests and in 99.5% with wording never seen in training.
	- Catches partial fakes. With reasoning, 99.6% of partially edited recordings in PartialEdit are caught, against
	78.4% for the one-step answer.

	Need the best numbers? See [Base or Plus?](https://huggingface.co/AustinXiao/VeriSpoof-Plus#base-or-plus)

	## The film

	<video controls preload="metadata" poster="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/film_poster.jpg" src="https://huggingface.co/AustinXiao/VeriSpoof-Base/resolve/main/assets/verispoof_film.mp4" width="100%"></video>

	1:59, Chinese and English captions. All voices in the film are synthetic (Fish Audio), including Yang Xiao’s. Music “78 PULSE” by kjartan_abel (CC BY 4.0); sound effects “2 Impact Wet” by original_sound (CC BY 3.0) and “data corrupted” by Saltbearer (CC BY 4.0), the rest CC0, via Openverse and Freesound; recordings from PartialEdit (CC BY 4.0) and MLAAD (CC BY-NC 4.0). Every model output shown is a real VeriSpoof output on that clip. The character is AI-generated art.

	## Model at a glance

	\| \| \|
	\|---\|---\|
	\| Parameters \| 2.9 B: audio encoder from Qwen3-ASR-1.7B, language model MiniCPM5-2B \|
	\| Input \| a speech recording at any sample rate (resampled to 16 kHz) \|
	\| Output \| an answer with its score; reasoning lines; a per-token synthetic-speech probability (every 0.16 s) \|
	\| Tasks \| detection, generator identification, source verification, recording condition, grounded reasoning \|
	\| Hardware \| one CUDA GPU with about 12 GB \|

	## Quick start

	```bash
	hf download AustinXiao/VeriSpoof-Base --include "code/*" --local-dir verispoof
	pip install ./verispoof/code
	```

	```python
	from verispoof import VeriSpoof

	model = VeriSpoof.from_pretrained("AustinXiao/VeriSpoof-Base") # weights are downloaded on first use

	# Detection. score = log p(spoof answer) - log p(bona fide answer); label uses threshold 0
	model.detect("sample.wav") # {'label': 'spoof', 'score': ...}
	model.detect(["a.wav", "b.flac"], batch_size=16) # a list in, a list out; arrays need sr=...

	# Grounded reasoning, plus the per-token head (probability that each 0.16 s token is synthesized)
	r = model.explain("sample.wav")
	print(r["text"]) # OBSERVATIONS / CHANNEL_STATUS / LOCALIZATION / SOURCE_PROFILE / DECISION lines
	r["decision"], r["spans"], r["token_prob"]

	# Source verification of two spoofed recordings: generator, acoustic_model or vocoder
	model.same_source("a.wav", "b.wav", level="generator") # {'same': ..., 'score': log p(yes) - log p(no)}
	model.compare("a.wav", "b.wav") # source-verification reasoning

	# Closed questions
	model.condition("sample.wav", attr="codec") # also "noise", "reverb"
	model.generator("sample.wav", ["XTTS-v2", "Bark", "VITS"]) # candidate systems you supply
	```

	### Faster reasoning with vLLM

	```bash
	pip install "./verispoof/code[vllm]"
	```

	```python
	from verispoof.vllm_backend import VeriSpoofVLLM

	if __name__ == "__main__": # vLLM starts its engine in a separate process
	m = VeriSpoofVLLM.from_pretrained("AustinXiao/VeriSpoof-Base")
	results = m.explain(["a.wav", "b.wav", "c.wav"]) # batched
	pairs = m.compare([("a.wav", "b.wav"), ("c.wav", "d.wav")])
	```

	\| Reasoning, one A100 \| per recording \| speed-up \|
	\|---\|---:\|---:\|
	\| `VeriSpoof.explain`, one at a time \| 2.24 s \| 1× \|
	\| `VeriSpoofVLLM.explain`, one at a time \| 0.50 s \| 4.5× \|
	\| `VeriSpoofVLLM.explain`, batch of 64 \| 0.05 s \| 46× \|

	Decisions are identical to `VeriSpoof` (64 / 64 recordings, 32 / 32 pairs). Detection scores and the per-token head
	use `VeriSpoof`. If vLLM fails to load a FlashInfer sampling kernel, set `VLLM_USE_FLASHINFER_SAMPLER=0`.

	## Results

	### Speech-DF-Arena leaderboard

	Public snapshot of 31 Oct 2026, ordered by pooled EER as on the board; every line of the official protocols
	([speech_df_arena](https://github.com/Speech-Arena/speech_df_arena), commit 97a4445) is scored.

	\| System \| Availability \| Params \| Average EER \| Pooled EER \|
	\|---\|---\|---:\|---:\|---:\|
	\| Modulate VELMA-2 \| Proprietary \| 0.3 B \| 1.10 \| 1.59 \|
	\| Resemble Detect-3B-Omni \| Proprietary \| 3 B \| 2.60 \| 2.10 \|
	\| 🥇 VeriSpoof-Plus \| Open-weight \| 2.9 B \| 1.79 \| 2.14 \|
	\| Hiya Authenticity Verification \| Proprietary \| 1 B \| 2.11 \| 2.32 \|
	\| 🥈 VeriSpoof-Base (this model) \| Open-weight \| 2.9 B \| 4.28 \| 4.43 \|
	\| DLMSL SpeakSure \| Proprietary \| 0.7 B \| 3.80 \| 6.14 \|
	\| Whispeak \| Proprietary \| 0.1 B \| 3.05 \| 8.06 \|
	\| DF Arena 1B \| Open-weight \| 1 B \| 5.66 \| 9.52 \|
	\| XLS-R + SLS \| Open-weight \| 0.3 B \| 14.01 \| 16.08 \|

	Average = mean of the 14 set EERs. Each VeriSpoof model is ranked on its own (Plus third of 28, Base fourth of 28).

	<details>
	<summary>Per test set</summary>

	\| Dataset \| Trials \| EER (%) \| Accuracy (%) \|
	\|---\|---:\|---:\|---:\|
	\| asvspoof_2019 \| 71,237 \| 0.49 \| 99.25 \|
	\| asvspoof_2021_la \| 148,176 \| 5.48 \| 93.54 \|
	\| asvspoof_2021_df \| 533,928 \| 0.97 \| 99.40 \|
	\| asvspoof_2024 \| 680,774 \| 2.59 \| 98.42 \|
	\| in_the_wild \| 31,779 \| 1.20 \| 98.93 \|
	\| fake_or_real \| 4,528 \| 5.39 \| 90.02 \|
	\| codecfake \| 304,241 \| 4.97 \| 89.51 \|
	\| add_2022_track_1 \| 109,199 \| 14.05 \| 88.42 \|
	\| add_2022_track_3 \| 126,861 \| 3.87 \| 96.84 \|
	\| add_2023_round_1 \| 111,976 \| 5.01 \| 90.35 \|
	\| add_2023_round_2 \| 118,477 \| 10.61 \| 92.87 \|
	\| dfadd \| 3,755 \| 0.00 \| 99.97 \|
	\| librisevoc \| 92,407 \| 0.02 \| 99.99 \|
	\| sonar \| 3,948 \| 5.19 \| 83.11 \|
	\| Average \| \| 4.28 \| 94.33 \|
	\| Pooled \| 2,341,286 \| 4.43 \| \|

	Accuracy at threshold 0.

	</details>

	### SpoofRadar v1.0 leaderboard

	16 test sets; pooled EER, and accuracy and macro-F1 at the pooled-EER threshold, as SpoofRadar defines them. Other
	rows from the published leaderboard (v1.0); ours computed with the same protocol files.

	\| System \| Availability \| Pooled EER \| Accuracy \| Macro-F1 \| Average EER \|
	\|---\|---\|---:\|---:\|---:\|---:\|
	\| Teffic-Audio \| Commercial \| 1.37 \| 98.63 \| 98.12 \| 1.09 \|
	\| WavLM-L (Teffic) \| Closed source \| 3.65 \| 96.35 \| 95.06 \| 2.88 \|
	\| 🥇 VeriSpoof-Plus \| Open-weight \| 4.04 \| 95.96 \| 94.54 \| 1.65 \|
	\| 🥈 VeriSpoof-Base (this model) \| Open-weight \| 4.23 \| 95.77 \| 94.29 \| 3.76 \|
	\| Whisper (Teffic) \| Closed source \| 5.75 \| 94.25 \| 92.33 \| 3.94 \|
	\| DF Arena 500M V1 \| Open-weight \| 9.96 \| 90.04 \| 87.08 \| 5.19 \|
	\| GRL \| Open-weight \| 13.25 \| 86.75 \| 83.17 \| 9.90 \|

	### Beyond detection

	On [VeriSpoof-Bench](https://huggingface.co/datasets/AustinXiao/VeriSpoof-Bench); details in the tech report.

	\| Task \| Result \|
	\|---\|---\|
	\| Detection, SpoofCeleb / CodecFake+ / CodecFake+ CoSG (unseen generators) \| EER 0.20 / 3.95 / 4.84% \|
	\| Detection under added noise, reverberation and codecs (6 sets) \| mean EER 5.23% \|
	\| Same-generator verification, MLAAD seen / unseen model / unseen architecture \| EER 17.23 / 13.80 / 20.25% \|
	\| Same-generator verification, SpoofCeleb / ASVspoof 2019 LA \| EER 11.25 / 8.22% \|
	\| Generator identification (MLAAD, closed set) \| 95.4% accuracy \|
	\| Acoustic model under an unseen vocoder (SpoofCeleb) \| 84.7% accuracy \|
	\| Recording condition (noise / reverberation / codec) \| 75.9% accuracy \|
	\| Partial fakes caught after reasoning vs one-step answer (PartialEdit / HAD) \| 99.6 vs 78.4 / 99.0 vs 99.0% \|
	\| Decision after reasoning, 11 sets \| 91.2–99.6% accuracy \|
	\| Partial-spoof localization, text spans (HAD / PartialEdit / PartialSpoof) \| IoU 0.61 / 0.58 / 0.25 \|
	\| Per-token head (HAD / PartialEdit / PartialSpoof) \| F1 0.91 / 0.79 / 0.74 \|
	\| Decision follows inverted localization (trained / new wording / inserted span) \| 1.00 / 0.995 / 1.00 \|
	\| Source-verification reasoning, verdict EER (SpoofCeleb / STOPA / CoSG / LA19 cond.) \| 20.20 / 13.65 / 21.60 / 29.65% \|

	## Intended use

	Research on audio deepfake detection, source tracing and explainable forensics. Not intended as the only basis for
	decisions about people; a forensic decision should combine this score with other evidence and human review.

	## License

	CC BY-NC 4.0 (non-commercial use). The base models keep their Apache-2.0 licences.

	## Citation

	```bibtex
	@misc{verispoof2026,
	title = {{VeriSpoof}: Beyond Real or Fake with One Audio {LLM}},
	author = {Xiao, Yang and Dang, Ting},
	year = {2026},
	eprint = {2611.04634},
	archivePrefix = {arXiv},
	primaryClass = {eess.AS},
	url = {https://arxiv.org/abs/2611.04634}
	}
	```

	## Contact

	Yang Xiao, The University of Melbourne, yxiao9550@student.unimelb.edu.au