Menu
Transcribe audio files to text using Groq or OpenAI Whisper.
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.
Read a specific note from an Obsidian vault and return the full markdown content.
Search an Obsidian vault (markdown files) and return matching note paths/snippets.
Create, update, and inspect message routing rules and dead-letter queues.
Call the Notion API for searching, reading, and updating pages and databases.
Search the public web for current information and return concise source-backed findings.
Fetch a single URL and extract readable article content for analysis and summarization.
Based on SOC occupation classification
| name | speech-to-text |
| description | Transcribe audio files to text using Groq or OpenAI Whisper. |
| metadata | {"cyberagent":{"tool":"speech-to-text","subcommand":"run","timeout_class":"long"}} |
| input_schema | {"type":"object","properties":{"file":{"type":"string"},"provider":{"type":"string"},"model":{"type":"string"},"language":{"type":"string"},"response_format":{"type":"string"},"fallback_provider":{"type":"string"},"fallback_model":{"type":"string"}}} |
| output_schema | {"type":"object","properties":{"text":{"type":"string"},"segments":{"type":"array"},"provider":{"type":"string"},"model":{"type":"string"},"language":{"type":"string"}}} |
Use this skill to transcribe audio files into text. Provide a local file path and optionally specify a provider, model, and language. When a provider fails, a fallback provider can be used if configured.
Examples:
