Agents365-ai

OpenAI Whisper Guide — Development skill for Claude Code

Development community

Claude Code skill for automatic speech recognition using optimal Whisper implementation.

How to install OpenAI Whisper Guide

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Agents365-ai/openai-whisper-guide and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What OpenAI Whisper Guide does

Claude Code skill for automatic speech recognition using optimal Whisper implementation.

Alternatives in Development

OpenAI Codex CLI — (Rust implementation) 67.8k ★
Speech — Generate spoken audio from text using OpenAI's API with built-in voices 14.6k ★
Claude Supermemory — Persistent memory across sessions and projects using Supermemory 2.3k ★

README

OpenAI Whisper Guide

[中文文档](README_CN.md)

A guide for automatic speech recognition using the optimal Whisper implementation for your hardware. Works with Claude Code and Opencode.

Features

Environment Detection: Automatically detects your OS, architecture, and GPU to recommend the best Whisper implementation
Multi-Implementation Support: Covers mlx-whisper, faster-whisper, whisper.cpp, and openai-whisper
Installation Guides: Platform-specific installation instructions
Usage Examples: Common transcription patterns and output formats

Quick Start

This skill is designed for use with [Claude Code](https://claude.ai/claude-code) or [Opencode](https://github.com/opencode-ai/opencode). Simply tell Claude:

"Transcribe this audio file"

"Convert video.mp4 to SRT subtitles"

"What's the best Whisper for my Mac?"

"Install whisper and transcribe podcast.mp3"

Or invoke directly with `/openai-whisper-guide`.

# Detect your environment
python3 scripts/detect_env.py

Decision Matrix

Environment	Recommended	Alternative
macOS Apple Silicon	mlx-whisper	whisper.cpp
macOS Intel	whisper.cpp	faster-whisper
Linux + NVIDIA 8GB+	faster-whisper	insanely-fast-whisper
Linux CPU	whisper.cpp	openai-whisper
Windows + CUDA	faster-whisper	whisper.cpp
Windows CPU	whisper.cpp	openai-whisper

Model Recommendation

Use `turbo` model for most tasks—it offers near large-v3 accuracy at 8x speed.

File Structure

openai-whisper-guide/
├── SKILL.md                    # Main documentation
├── scripts/
│   └── detect_env.py          # Environment detection
└── .claude/
    └── settings.local.json    # Bash permissions