# 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.

- Skill: `whq25/agent-listen` (Agent Skill, multi-file: 9 files)
- Install (CLI): `npx skillmds@latest add whq25/agent-listen`
- Raw SKILL.md: https://api.skillmd.com/api/skills/whq25/agent-listen/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: whq25 (https://skillmd.com/u/whq25)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/whq25/agent-listen

---


# Agent Listen

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

## Prerequisites

```bash
brew install WHQ25/tap/rawgenai
```

Before using a provider, read its setup guide at [references/setup/](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](references/stt/openai.md) |
| **Google Gemini** | `rawgenai google stt` | Speaker diarization | [ref](references/stt/google.md) |
| **ElevenLabs** | `rawgenai elevenlabs stt` | Large files (3GB), video input | [ref](references/stt/elevenlabs.md) |
| **DashScope** | `rawgenai dashscope stt` | Chinese, emotion, long audio (12h async) | [ref](references/stt/dashscope.md) |