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 Duby AI and sends the result as a native voice message to Feishu chats. Supports both user IDs and group chat IDs as targets, with an optional voice parameter to change the TTS voice.
Delivers audio as Feishu's native voice message format rather than a file attachment, so recipients hear it inline like a real voice note.
When to use it
- Sending spoken deployment alerts to a Feishu ops channel
- Automating voice reminders for daily standups
- Delivering audio greetings to new team members without recording
- Broadcasting spoken incident updates to an on-call group chat
- Converting written summaries into voice messages for mobile listeners
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Send a voice message saying 'The build has passed. Deployment is ready.' to the engineering chat
- 1Reads the target chat ID and message text from the request
- 2Calls Duby AI TTS API with the text and selected voice ID
- 3Receives the generated audio file
- 4Uploads the audio to Feishu using app credentials from .env
- 5Sends the uploaded audio as a native voice message to the target chat ID
Voice message delivered inline to the specified Feishu chat
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.