Agent Speak
Use rawgenai <provider> tts to speak, rawgenai <provider> dialogue for multi-speaker audio, and rawgenai <provider> voice to manage voices. 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.
Input Sources
- Positional argument:
rawgenai <provider> tts "text" [flags]
- File:
rawgenai <provider> tts --file input.txt [flags]
- Stdin:
echo "text" | rawgenai <provider> tts [flags]
General Guidelines
- On first use, ask user to pick a provider. Remember for the session.
- All output is JSON. Always show file paths to the user.
- For TTS: write natural conversational text, not markdown. Use
--speak for playback, -o for file.
- If a command fails, try a different provider or inform the user.
Speak (TTS)
rawgenai <provider> tts "<text>" --speak
| Provider |
Command |
Best For |
Reference |
| OpenAI |
rawgenai openai tts |
General purpose, English |
ref |
| Google Gemini |
rawgenai google tts |
Expressive storytelling, multi-speaker |
ref |
| ElevenLabs |
rawgenai elevenlabs tts |
Most natural voices, 70+ languages |
ref |
| Seed |
rawgenai seed tts |
Chinese, emotion-rich |
ref |
| DashScope |
rawgenai dashscope tts |
Chinese, 10 languages, 49 voices |
ref |
| MiniMax |
rawgenai minimax tts |
Chinese, streaming |
ref |
| Kling |
rawgenai kling tts |
Bilingual zh/en |
ref |
| Runway |
rawgenai runway audio tts |
Async |
— |
Dialogue
Multi-speaker dialogue from JSON script (max 10 voices).
| Provider |
Command |
Reference |
| ElevenLabs |
rawgenai elevenlabs dialogue -i script.json -o out.mp3 |
ref |
Voice Management
Design, clone, and manage custom voices.
| Provider |
Command |
Capabilities |
Reference |
| ElevenLabs |
rawgenai elevenlabs voice |
list, design, create, preview |
ref |
| Kling |
rawgenai kling voice |
create, status, list, delete |
ref |
| MiniMax |
rawgenai minimax voice |
list, upload, clone, design, delete |
ref |
| Seed |
rawgenai seed voice-clone |
upload, status, order, renew |
ref |
1---2name: agent-speak3description: Give agents voice abilities using `rawgenai` — text-to-speech, multi-speaker dialogue, and voice management (design, clone, create voices). Use this skill when the user asks to "speak", "talk", "read aloud", "say this", "create dialogue", "design a voice", "clone a voice", or any request involving spoken audio output and voice creation.4---56# Agent Speak78Use `rawgenai <provider> tts` to speak, `rawgenai <provider> dialogue` for multi-speaker audio, and `rawgenai <provider> voice` to manage voices. Always read the chosen provider's reference file before running commands.910## Prerequisites1112```bash13brew install WHQ25/tap/rawgenai14```1516Before using a provider, read its setup guide at [references/setup/](references/setup/) to configure credentials.1718## Input Sources19201. Positional argument: `rawgenai <provider> tts "text" [flags]`212. File: `rawgenai <provider> tts --file input.txt [flags]`223. Stdin: `echo "text" | rawgenai <provider> tts [flags]`2324## General Guidelines2526- On first use, ask user to pick a **provider**. Remember for the session.27- All output is JSON. Always show file paths to the user.28- For TTS: write natural conversational text, not markdown. Use `--speak` for playback, `-o` for file.29- If a command fails, try a different provider or inform the user.3031---3233## Speak (TTS)3435`rawgenai <provider> tts "<text>" --speak`3637| Provider | Command | Best For | Reference |38|----------|---------|----------|-----------|39| **OpenAI** | `rawgenai openai tts` | General purpose, English | [ref](references/speak/openai.md) |40| **Google Gemini** | `rawgenai google tts` | Expressive storytelling, multi-speaker | [ref](references/speak/google.md) |41| **ElevenLabs** | `rawgenai elevenlabs tts` | Most natural voices, 70+ languages | [ref](references/speak/elevenlabs.md) |42| **Seed** | `rawgenai seed tts` | Chinese, emotion-rich | [ref](references/speak/seed.md) |43| **DashScope** | `rawgenai dashscope tts` | Chinese, 10 languages, 49 voices | [ref](references/speak/dashscope.md) |44| **MiniMax** | `rawgenai minimax tts` | Chinese, streaming | [ref](references/speak/minimax.md) |45| **Kling** | `rawgenai kling tts` | Bilingual zh/en | [ref](references/speak/kling.md) |46| **Runway** | `rawgenai runway audio tts` | Async | — |4748---4950## Dialogue5152Multi-speaker dialogue from JSON script (max 10 voices).5354| Provider | Command | Reference |55|----------|---------|-----------|56| **ElevenLabs** | `rawgenai elevenlabs dialogue -i script.json -o out.mp3` | [ref](references/dialogue/elevenlabs.md) |5758---5960## Voice Management6162Design, clone, and manage custom voices.6364| Provider | Command | Capabilities | Reference |65|----------|---------|-------------|-----------|66| **ElevenLabs** | `rawgenai elevenlabs voice` | list, design, create, preview | [ref](references/voice/elevenlabs.md) |67| **Kling** | `rawgenai kling voice` | create, status, list, delete | [ref](references/voice/kling.md) |68| **MiniMax** | `rawgenai minimax voice` | list, upload, clone, design, delete | [ref](references/voice/minimax.md) |69| **Seed** | `rawgenai seed voice-clone` | upload, status, order, renew | [ref](references/voice/seed.md) |
whq25