Local Whisper
Alert level: High
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
Locality:Local
Data access:Sensitive
Actions:Execute
Installs 3Downloads 1013Stars 2Updated 204h ago
Why this rating
Deterministic checks triggered by the tool capabilities and evidence.
- Locality: Local
Transcription runs on the user machine and is "fully offline" after setup/model download.
- Data access: Sensitive
Processes local audio recordings which may contain private conversations or identifiers.
- Action surface: Execute
Runs a local CLI to transcribe audio and can emit timestamped/JSON outputs.
Best practices
Follow these steps to reduce risk when using this skill.
- Keep audio files and transcripts in a protected folder and avoid sharing raw outputs publicly.
- Treat transcripts as sensitive text (names, addresses, meeting content) and redact before copying into tickets/issues.
- Verify dependencies/models and pin versions when possible to reduce supply-chain risk during initial installs.
Evidence links
Public sources backing the indicator assignments.
Always be careful when navigating away from the website.
Max-risk rule
If any capability reaches a higher level, the entire indicator level bumps up to keep ratings deterministic and easy to scan.