Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Converts text to speech using Alibaba Cloud's TTS API. Outputs audio files in configurable formats, voices, and sample rates. Can be invoked directly from the command line or integrated into agent workflows for voice replies.
Provides direct CLI access to Alibaba Cloud TTS without requiring custom API integration code.
When to use it
- Generate MP3 voice replies in chat
- Convert article text to audio for playback
- Create voice announcements with a specific speaker
- Batch produce audio files from text content
- Automate spoken alerts or notifications
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Can you read this message aloud in the siyue voice?'
- 1Receives the text content from the user
- 2Runs aliyun-tts with -v siyue and -o /tmp/voice-reply.mp3 flags
- 3Passes the text as the final argument
- 4Confirms the audio file was written successfully
- 5Includes MEDIA:/tmp/voice-reply.mp3 in the response
An MP3 audio file delivered back to the user as a media attachment
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.