A specialized skill that enables AI agents to automatically convert text responses into spoken audio messages across popular messaging platforms.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install telegram-voice-mode
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install telegram-voice-mode using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Voice Reply?
The Voice Reply skill is a powerful addition to the Openclaw Skills ecosystem, designed to provide a more immersive and accessible communication experience. By integrating with the edge-tts engine, this skill allows users to switch their agent from a standard text-based mode to a voice-first interaction model. Once activated, every response generated by the agent is synthesized into a natural-sounding audio file, specifically optimized for platforms like Telegram, iMessage, and Discord.
This tool is ideal for developers and power users who want to build more human-like interactions or require hands-free feedback from their AI agents. It leverages high-quality neural voices to ensure that the generated audio is clear and professional, further expanding the versatility of Openclaw Skills in real-world communication workflows.
Voice Reply Use Cases
- Enabling hands-free interactions with AI agents during commutes or multitasking sessions.
- Automating voice note replies in Telegram channels or iMessage threads.
- Converting long-form AI explanations into digestible audio content using high-quality neural voices.
- Enhancing accessibility for users who prefer auditory feedback over reading text.
How Voice Reply Works
- The user activates the voice interaction mode using the /voiceMode command.
- When the AI agent generates a response, the skill intercepts the text content before it is sent.
- The text is processed through the edge-tts engine using the zh-CN-XiaoxiaoNeural female voice profile.
- An MP3 audio file is generated and stored in a temporary directory for processing.
- The system moves the file to the active workspace and transmits the audio message to the user's connected channel.
- The original text message is suppressed to ensure a clean, voice-only delivery experience.
Voice Reply Setup
To integrate Voice Reply with your agent, ensure you have the necessary environment for Openclaw Skills and follow these steps:
- Install the required edge-tts dependencies in your environment.
- Configure your messaging bot (Telegram, Discord, etc.) to handle audio file uploads.
- Test the manual voice generation script using the following command:
node scripts/voice-send.js "Hello, this is a test message" [your_telegram_id]
- Use
/voiceModewithin your agent chat to toggle automatic voice responses.
Voice Reply Data Schema & Taxonomy
The Voice Reply skill manages data and file outputs according to the following structure:
| Property | Configuration |
|---|---|
| TTS Engine | edge-tts |
| Default Voice | zh-CN-XiaoxiaoNeural (Chinese Female) |
| Audio Format | MP3 |
| Temp Directory | /tmp/voice-reply/ |
| Workspace File | ~/.openclaw/workspace/voice.mp3 |
| Supported Channels | Telegram, iMessage, Discord |
Voice Reply Advanced Features
- Support for manual CLI voice broadcasts via the voice-send.js script.
- Real-time status monitoring using the /voice status command to check the current operational mode.
- Session-aware state management that maintains voice preferences throughout the conversation context.
- High-performance neural text-to-speech synthesis for low-latency audio delivery within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Bilibili Update Viewer
A Bilibili monitoring utility to track creator updates, new video releases, and social dynamics in real-time.
Jina.ai Reader
A powerful utility to fetch clean, AI-optimized Markdown content from any website, including paywalled and JavaScript-heavy pages.
Yu-Gi-Oh! OCG Daily News Summarizer
An automated news aggregator that delivers daily summaries of Japanese Yu-Gi-Oh! OCG updates directly to your AI agent.
Human-Like Memory Skill
The Human-Like Memory Skill provides AI agents with persistent long-term memory to recall past conversations and user preferences across multiple sessions.
Aviation Healthcheck
A comprehensive monitoring tool for tracking aviation regulatory updates and Openclaw Skills environment health.
Codex Deep Search
A sophisticated deep-research skill that utilizes Codex CLI to perform multi-source synthesis and high-context analysis for complex queries.
Featured*
