Whisper
Whisper OpenAI speech recognition. Use for speech-to-text.
Install
$ agentstack add skill-g1joshi-agent-skills-whisper ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Whisper
Whisper (OpenAI) is the industry standard for Speech-to-Text. It supports 99 languages and translation. V3 (large-v3) is the current state of the art.
When to Use
- Transcription: Creating subtitles for videos.
- Translation: Translating audio to English text.
- Local Privacy: Runs 100% locally (sensitive meetings).
Core Concepts
Models
tiny, base, small, medium, large, legacy, large-v3, large-v3-turbo.
Distil-Whisper
Smaller, faster versions of Whisper (6x speedup, 1% accuracy loss).
Best Practices (2025)
Do:
- Use
insanely-fast-whisper: A wrapper that uses Flash Attention to transcribing 2 hours of audio in 2 minutes. - Use API for streaming: OpenAI API supports streaming audio transcription.
Don't:
- Don't use
largefor realtime: It's too slow. Useturboordistilmodels.
References
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: G1Joshi
- Source: G1Joshi/Agent-Skills
- License: MIT
- Homepage: https://skills.sh/g1joshi/agent-skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.