Skip to main content

whisperx

WhisperX provides advanced speech-to-text capabilities with precise timestamps and speaker identification for efficient transcription.

Install this skill

or
70/100

Security score

The whisperx skill was audited on Jun 4, 2026 and we found 14 security issues across 3 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 369

Template literal with variable interpolation in command context

SourceSKILL.md
369```bash
medium line 62

Access to hidden dotfiles in home directory

SourceSKILL.md
62| **With speakers** | `./scripts/transcribe audio.mp3 --diarize` | Auto-reads `~/.cache/huggingface/token` |
low line 123

Access to hidden dotfiles in home directory

SourceSKILL.md
123mkdir -p ~/.cache/huggingface && echo -n "hf_YOUR_TOKEN" > ~/.cache/huggingface/token && chmod 600 ~/.cache/huggingface/token
medium line 133

Access to hidden dotfiles in home directory

SourceSKILL.md
133- Auto-reads the HF token from `~/.cache/huggingface/token` for diarization
medium line 135

Access to hidden dotfiles in home directory

SourceSKILL.md
135- First run for a new model downloads it to `~/.cache/huggingface/` (one-time per model)
low line 171

Access to hidden dotfiles in home directory

SourceSKILL.md
171# With speaker diarization (auto-reads ~/.cache/huggingface/token)
low line 259

Access to hidden dotfiles in home directory

SourceSKILL.md
259--hf-token TOKEN Hugging Face access token (also reads ~/.cache/huggingface/token or HF_TOKEN env)
low line 116

External URL reference

SourceSKILL.md
1161. Create account at [huggingface.co](https://huggingface.co) (if you don't have one)
low line 117

External URL reference

SourceSKILL.md
1172. Go to [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) and create a **read** access token
low line 119

External URL reference

SourceSKILL.md
119- **whisperx ≥3.8.0** (recommended): Accept [pyannote/speaker-diarization-community-1](https://huggingface.co/pyannote/speaker-diarization-community-1) — uses pyannote v4 with better accuracy
low line 120

External URL reference

SourceSKILL.md
120- **whisperx <3.8.0**: Accept **both** [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) and [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segme
low line 497

External URL reference

SourceSKILL.md
497**"CUDA not available"**: Install PyTorch with CUDA (`pip install torch --index-url https://download.pytorch.org/whl/cu121`)
low line 501

External URL reference

SourceSKILL.md
501**Diarization 403 error**: You must accept the model agreement(s). For whisperx ≥3.8.0: accept [community-1](https://huggingface.co/pyannote/speaker-diarization-community-1). For earlier versions: acc
low line 528

External URL reference

SourceSKILL.md
528- [WhisperX Paper (INTERSPEECH 2023)](https://arxiv.org/abs/2303.00747)
Scanned on Jun 4, 2026
View Security Dashboard
Installation guide →