skills.rest
jx1100370217
jx1100370217COMMUNITY
Explore all skills by this author →
WebsiteGitHub

voice-setup

Configure local TTS and STT voice capabilities for OpenClaw.

4|1|Updated Feb 2, 2026
Search Tags:#offline#tts#stt#openclaw#edge-tts#whisper-cpp#voice-setup
One-click install
npx skills add https://github.com/jx1100370217/my-openclaw-skills --skill voice-setup
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice-setup
Source: https://github.com/jx1100370217/my-openclaw-skills/tree/main/voice-setup
Command: npx skills add https://github.com/jx1100370217/my-openclaw-skills --skill voice-setup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper-cpp, ffmpeg, and includes scripts (resource) components.

What problem does it solve?

This Skill configures free, local voice capabilities (TTS + STT) for OpenClaw, enabling voice interactions without relying on paid APIs.

Core Features & Use Cases

  • Local text-to-speech and speech-to-text using Edge TTS and whisper-cpp, with no API keys required.
  • Voice messaging and transcription for OpenClaw workflows, usable in Telegram/WhatsApp integrations or on-device assistants.
  • Simple, script-driven setup that bootstraps dependencies and provides a ready-to-use voice pipeline.

Quick Start

  1. Run the setup script to install dependencies and download the whisper model: bash scripts/setup.sh
  2. Apply the provided voice configuration patch to OpenClaw as described in SKILL.md, and restart the gateway.
  3. Test by sending a voice message and confirming transcription and TTS playback.

Frequently Asked Questions about voice-setup

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

FAQPage Schema
How do I set up offline voice input and output for OpenClaw without paid APIs?▼

Offline voice for OpenClaw is configured by running a setup script that installs Edge TTS for text-to-speech and whisper-cpp for speech-to-text, then applying a configuration patch and restarting the gateway to enable voice interactions.

Can I use whisper-cpp and Edge TTS to enable voice messaging in Telegram and WhatsApp integrations?▼

Yes, whisper-cpp and Edge TTS enable voice messaging and transcription for OpenClaw workflows, allowing platforms like Telegram and WhatsApp to process voice input and generate voice output completely locally.

Do I need ffmpeg and whisper-cpp installed locally to use offline voice transcription?▼

Yes, offline voice transcription requires ffmpeg and whisper-cpp as local dependencies, along with a downloaded Whisper model, which the setup script automatically bootstraps and verifies for your OpenClaw deployment.

What is the best way to configure local text-to-speech and speech-to-text for an on-device assistant?▼

The best way to configure local TTS and STT is using the script-driven setup that installs Edge TTS and whisper-cpp, providing a ready-to-use voice pipeline without API keys for on-device assistants.

Why does my OpenClaw voice setup require a configuration patch and gateway restart?▼

The voice setup requires a configuration patch and gateway restart to integrate the local Edge TTS and whisper-cpp components into OpenClaw's workflow, ensuring voice input and output pipelines are properly registered and active.

Related Skills

Explore More Software Engineering Skills→
erguotou520erguotou520

use-local-whisper

Replace cloud WhatsApp voice transcription with local whisper.cpp processing.

Community
Advanced
1mancompany1mancompany
380

Multi-Channel Communications

Route and manage messages across twenty-plus platforms via an OpenClaw gateway.

Official
Advanced
mbaker95mbaker95

add-voice-transcription

Transcribe WhatsApp voice messages into text using OpenAI's Whisper API.

Community
Intermediate
Purple-HorizonsPurple-Horizons
123

OpenClaw Voice Skill

Process spoken language to text and provide voice responses via OpenClaw.

Official
Intermediate