---
language:
  - en
license: apache-2.0
library_name: dotcheck
pipeline_tag: audio-classification
tags:
  - audio-classification
  - ai-detection
  - synthetic-media
  - dasheng
  - apache-2.0
  - dotcheck
  - helmholtz
base_model: mispeech/dasheng-base
base_model_relation: adapter
model-index:
  - name: Helmholtz (inhouse-audio@3)
    results:
      - task:
          type: audio-classification
          name: binary AI detection (audio)
        dataset:
          name: DotCheck audio holdout (CodecFake / DFADD / AudioGen + fal family)
          type: other
          split: holdout
        metrics:
          - name: mean_P_AI_real
            type: mean_score_real
            value: 0.005
          - name: mean_P_AI_ai
            type: mean_score_ai
            value: 0.982
          - name: balanced_accuracy
            type: balanced_accuracy
            value: 0.989
        source:
          name: audio_gates_audio_v3 / Data.json
          url: https://dotcheck.ai/docs
---

# DotCheck/helmholtz-audio-v3

**Helmholtz** is DotCheck’s production audio detector. We train a logistic head on frozen Dasheng-Base embeddings, gate on held-out speech, music/SFX, and fal-family TTS, and publish the holdout table below.

Open package: live `.npz` head, card, license, notices. In product, soundtrack windows can fuse with Muybridge frame bags (Covenant); that seating stays private. This repo is standalone audio.

| Field | Value |
|-------|--------|
| Hub id | `DotCheck/helmholtz-audio-v3` |
| Wire id | `inhouse-audio@3` |
| Label | Helmholtz |
| Artifact | `dasheng_base_linear_head_audio_v3.npz` |
| Backbone | [`mispeech/dasheng-base`](https://huggingface.co/mispeech/dasheng-base) (Apache-2.0) |
| Protocol | 4 s / center crop / up to 2 windows / max aggregate (serve may single-pass prewindowed clips) |
| Output | `p ∈ [0,1]` — estimated P(AI) |
| Serve | CPU FastAPI `/v1/analyze-audio`; Express Check + video soundtrack fuse |

## Model description

Frozen Dasheng-Base masked audio encoder + logistic head for speech, music, and general audio. Product Covenant seats soundtrack windows with Muybridge frame bags when a video has usable audio. Covenant is DotCheck-private; these files are the open audio head only.

**In this repo:** `README.md`, `LICENSE`, `NOTICE`, `CITATION.cff`, and the `.npz` head.

## Architecture

```text
audio bytes
  → mono 16 kHz
  → protocol window(s) (4 s)
  → frozen Dasheng-Base emb → logistic head → p
  → multi-window: max
```

Missing audio head at serve → `/v1/analyze-audio` returns **503** (fail closed).

## Inference

Open weights: the live `.npz` head (Apache-2.0) with the frozen backbone above. Not `AutoModel.from_pretrained("DotCheck/…")`.

Product scoring: [Check](https://dotcheck.ai/check) or [Pro API](https://dotcheck.ai/api).

```bash
curl -sS -X POST "https://dotcheck-server-c221c1f32c68.herokuapp.com/analyze-audio" \
  -H "Authorization: Bearer dc_YOUR_KEY" \
  -F "audio=@clip.wav"
```

Gates: [dotcheck.ai/docs](https://dotcheck.ai/docs).

## Training data

| Split | Content |
|-------|---------|
| Fit reals | LibriTTS + FSD50K (concat, no loop-tile) |
| Fit AI | parler-mini / melo-en / dasheng-audiogen + fal train (Kokoro / Eleven Turbo / mixes) + 22 Imagine few-shot |
| Holdout speech | CodecFake / DFADD (sha-disjoint) |
| Holdout music/SFX | AudioGen odd-seed partition |
| Holdout fal | prompt-id holdout (same gens, disjoint sha) |

Evidence: `audio_gates_audio_v3.json` · `AUDIO_GATES_OK`. Imagine-owned audio is a **watch**, not a public claim.

## Evaluation

### Holdout (public claim SSOT)

| Metric | Target | Measured |
|--------|--------|---------:|
| mean P(AI) \| real | ≤ 0.12 | **0.005** |
| mean P(AI) \| AI | ≥ 0.85 | **0.982** |
| bal_acc @ thr | ≥ 0.90 | **0.989** |

## Intended use

- Standalone audio AI detection in DotCheck inference.
- Soundtrack windows fused with video frames in product serve.
- Citation of the holdout table above.

### Out of scope

- Product SLA via Hub download alone
- Courtroom deepfake forensics or speaker identification
- Legal determinations

## Limitations

- Protocol windows are short; long-form structure is not modeled.
- Codec, compression, and unseen generators can shift scores.
- Public floats are standalone audio gates; fused video bags are not a separate claim table here.

## License

[`LICENSE`](LICENSE) — Apache License 2.0 for DotCheck heads in this repo. Upstream: [`NOTICE`](NOTICE).

## Citation

[`CITATION.cff`](CITATION.cff) · wire `inhouse-audio@3` / Helmholtz@3 · https://dotcheck.ai/docs