webex-voice-interface

Transcribe WebEx voice clips and generate text replies with optional MP3 audio.

Updated Feb 28, 2026
One-click install
npx skills add https://github.com/dgethings/netclaw --skill webex-voice-interface
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: webex-voice-interface
Source: https://github.com/dgethings/netclaw/tree/main/workspace/skills/webex-voice-interface
Command: npx skills add https://github.com/dgethings/netclaw --skill webex-voice-interface

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribing and replying to WebEx voice messages manually is time-consuming; this skill automates generating both a readable text response and a spoken MP3 reply.

Core Features & Use Cases

  • Automated Voice-to-Text + Text+Audio Replies: Responds to voice messages by producing both textual and audio responses via edge-tts.
  • Edge-tts based TTS: Uses edge-tts for high-quality MP3 voice replies.
  • OpenClaw transcription integration: Leverages built-in transcription to feed into NetClaw for context-rich replies.
  • Use Case: When a user sends a WebEx voice clip, automatically reply with text and attach an MP3 vocal response.

Quick Start

Trigger the skill by sending a WebEx voice clip and request a text-and-audio reply to receive both transcript and MP3 vocal response.

Frequently Asked Questions about webex-voice-interface

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate WebEx voice clip transcription and replies?

To automate WebEx voice clip transcription and replies, this skill processes voice messages using OpenClaw transcription and generates both text and MP3 audio responses via edge-tts. It automatically provides a readable text reply and an optional spoken MP3 attachment in WebEx spaces.

Can I generate MP3 voice replies for WebEx spaces using text-to-speech?

Yes, you can generate MP3 voice replies for WebEx spaces using text-to-speech. The skill leverages edge-tts to synthesize high-quality spoken MP3 audio responses, attaching the vocal reply alongside the standard text response when a user sends a voice clip.

Does this WebEx voice processing skill require edge-tts to function?

Yes, this WebEx voice processing skill requires edge-tts to function. Edge-tts is necessary for the text-to-speech synthesis that generates the spoken MP3 audio replies, while MCP scripts handle generating and attaching the audio file to the response.

How does OpenClaw transcription work with WebEx voice messages?

OpenClaw transcription works with WebEx voice messages by automatically transcribing the incoming voice clips into text. This transcription feeds into the NetClaw skill set to craft context-rich text replies, which are then optionally converted into spoken MP3 audio using edge-tts.

What is the best way to respond to WebEx voice clips with both text and audio?

The best way to respond to WebEx voice clips with both text and audio is to trigger this skill by sending a WebEx voice clip. It automatically transcribes the message, crafts a context-rich text reply, and uses edge-tts to attach an optional MP3 vocal response.

Are text responses always included when processing WebEx voice clips?

Yes, text responses are always included when processing WebEx voice clips. The skill uses text as the primary delivery method for the reply, while the spoken MP3 audio response generated by edge-tts serves as an optional enhancement to the interaction.