Menu
Transcribe audio files using Google Gemini 1.5 Flash model. Supports batch transcription of multiple audio files.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Resolves open GitHub Issues in parallel by fanning out independent subagents and then fanning in to aggregate lessons learned.
(🥑) Expert guide for authoring, building, testing, and publishing technical articles to ricc.rocks and Medium.
Hackathon security guide to prevent leaking secrets. Based on Romin Irani's article.
💛 Expert guide for interacting with Riccardo's Obsidian vault (The Carlessian Vault).
Record browser-based video demos from YAML storyboards using shot-scraper.
Installs a lightweight CPU and RAM monitoring cron job and visualization script for agents on the local machine.
Based on SOC occupation classification
| name | google-stt |
| description | Transcribe audio files using Google Gemini 1.5 Flash model. Supports batch transcription of multiple audio files. |
| compatibility | Gemini CLI |
| metadata | {"version":"0.1.0"} |
This skill provides the capability to transcribe audio files into text using Google's Gemini 1.5 Flash model. It is designed for quick and efficient transcription of voice notes, recordings, or any supported audio content.
transcribe.py script to upload the audio to Gemini and generate a transcription.~/.openclaw/settings.json under apiKeys.google.gemini.google-generativeai Python library must be installed.