Agent Listen

Give agents listening abilities using `rawgenai` — transcribe audio/video to text with timestamps, subtitles, and speaker diarization. Use this skill when the user asks to "transcribe", "speech to text", "convert audio to text", "generate subtitles", "diarize speakers", or any request involving audio/video transcription.

whq25 6a3a012 9 files · 7.5 KB Updated

File contents

Agent Listen

Use rawgenai <provider> stt to transcribe audio and video files. Always read the chosen provider's reference file before running commands.

Prerequisites

brew install WHQ25/tap/rawgenai

Before using a provider, read its setup guide at references/setup/ to configure credentials.

General Guidelines

  • On first use, ask user to pick a provider. Remember for the session.
  • All output is JSON. Always show transcription results to the user.
  • If a command fails, try a different provider or inform the user.

Listen (STT)

rawgenai <provider> stt <audio-file>

Provider Command Best For Reference
OpenAI rawgenai openai stt Subtitles (srt/vtt) ref
Google Gemini rawgenai google stt Speaker diarization ref
ElevenLabs rawgenai elevenlabs stt Large files (3GB), video input ref
DashScope rawgenai dashscope stt Chinese, emotion, long audio (12h async) ref

whq25/rawgenai/tree/main/skills/agent-listen commit 6a3a012bc3

Frequently asked questions

npx skillmds@latest add whq25/agent-listen