Fast on-device speech-to-text using Apple Speech.framework for macOS users.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install yap
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install yap using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is yap?
yap is a high-performance command-line utility designed for developers and power users who need fast, on-device transcription on macOS. By leveraging Apple's native Speech.framework, it bypasses the need for heavy model downloads like Whisper, offering a lightweight alternative optimized for Apple Silicon. This utility is a core component of the Openclaw Skills ecosystem, providing seamless integration for macOS workflows requiring rapid audio processing.
The tool is specifically built for macOS 26 (Tahoe) and later, ensuring deep system-level optimization. Whether you are generating subtitles for videos or transcribing voice notes, this skill provides a privacy-first approach by keeping all data processing local to your machine.
yap Use Cases
- Transcribing audio files (MP3, M4A) directly from the terminal.
- Generating SRT caption files for video content production.
- Multi-language support for international projects using specific locales.
- Redacting sensitive information during transcription via the censor flag.
How yap Works
- The user provides an audio or video file path to the yap command-line interface.
- The utility interfaces with Apple's native Speech.framework to process audio on-device.
- Optional flags are applied to specify language locales or output formats like SRT or TXT.
- The processed text is either printed to the standard output or saved to a specified file.
yap Setup
To integrate this into your environment as part of your Openclaw Skills collection, install it via Homebrew:
brew install finnvoor/tools/yap
Ensure you are running macOS 26 or later to maintain compatibility with the required frameworks.
yap Data Schema & Taxonomy
The skill handles input and output through standard file system paths and CLI arguments. Output data can be structured as follows:
| Feature | Description |
|---|---|
| Input Formats | MP3, M4A, MP4, and other macOS-supported media types. |
| Output Formats | Plain text (.txt) or SubRip Subtitle (.srt) files. |
| Locale Metadata | Supports standard BCP 47 language tags (e.g., en-US, de-DE). |
| Privacy | 100% on-device processing with no external API calls. |
yap Advanced Features
- Multi-locale support for diverse language processing needs.
- Integrated censorship engine for automated content moderation.
- Native Apple Silicon optimization for significantly lower memory overhead than Whisper-based models.
- Direct output piping for inclusion in complex automation scripts and Openclaw Skills workflows.
SKILL.md
Loading
Related Openclaw Skills
say
A macOS-native text-to-speech skill that leverages the system say command and Siri Natural Voices for professional audio generation.
Image Search (Google Lens)
A sophisticated visual search tool that allows AI agents to identify objects, landmarks, and products using Google Lens via SerpAPI.
Fizzy CLI
A comprehensive command-line interface for managing Fizzy kanban boards, cards, and team collaborations within automated workflows.
Bambu CLI
A powerful command-line interface for monitoring, controlling, and troubleshooting BambuLab 3D printers over local network protocols.
Autonomous Research
An advanced AI skill for conducting independent end-to-end research, source validation, and professional report generation.
Content Generation
A professional-grade AI content creation skill for generating SEO-optimized articles, marketing copy, and platform-specific social media posts.
METADATA
Featured*
