skills$openclaw/voice-ai-agents
gizmogremlin5.4k

by gizmogremlin

voice-ai-agents – OpenClaw Skill

voice-ai-agents is an OpenClaw Skills integration for ai ml workflows. >

5.4k stars8.3k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026ai ml

Skill Snapshot

namevoice-ai-agents
description> OpenClaw Skills integration.
ownergizmogremlin
repositorygizmogremlin/voice-ai-agent
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @gizmogremlin/voice-ai-agent
last updatedFeb 7, 2026

Maintainer

gizmogremlin

gizmogremlin

Maintains voice-ai-agents in the OpenClaw Skills directory.

View GitHub profile
File Explorer
6 files
.
scripts
agent.js
6.7 KB
_meta.json
287 B
SKILL.md
3.4 KB
voice-ai-agents-sdk.js
14.3 KB
voice-ai-agents.yaml
4.6 KB
SKILL.md

name: voice-ai-agents description: > Create, manage, and deploy Voice.ai conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.

Voice.ai Agents

Build conversational AI voice agents with Voice.ai's Agent API.

✨ Features

  • Agent Management - Create, update, and delete voice agents
  • One-Click Deploy - Deploy agents for phone calls instantly
  • Knowledge Base - RAG-powered agents with custom knowledge
  • MCP Integration - Connect agents to external tools via MCP
  • Phone Numbers - Manage inbound/outbound phone numbers
  • Analytics - Track call history and agent performance

🚀 Quick Start

export VOICE_AI_API_KEY="your-api-key"

# Create an agent
node scripts/agent.js create --name "Support Bot" --prompt "You are a helpful assistant"

# List all agents
node scripts/agent.js list

# Deploy an agent
node scripts/agent.js deploy --id <agent_id>

🤖 Agent Configuration

ParameterDefaultDescription
llm_modelgemini-2.5-flash-liteLLM model for responses
llm_temperature0.7Response creativity (0-2)
max_call_duration900Max call length in seconds
allow_interruptionstrueLet users interrupt agent
auto_noise_reductiontrueFilter background noise

🎙️ TTS Voice Settings

ParameterDefaultDescription
voice_id-Voice ID for agent speech
modelautoTTS model (auto-selected)
languageenLanguage code
temperature1.0Voice expressiveness (0-2)
top_p0.8Sampling parameter (0-1)

🌍 Supported Languages

auto, en, ca, sv, es, fr, de, it, pt, pl, ru, nl

💻 CLI Usage

# Create a new agent
node scripts/agent.js create --name "My Agent" --prompt "System prompt here" --greeting "Hello!"

# List all agents
node scripts/agent.js list

# Get agent details
node scripts/agent.js get --id <agent_id>

# Update an agent
node scripts/agent.js update --id <agent_id> --prompt "New prompt"

# Deploy an agent
node scripts/agent.js deploy --id <agent_id>

# Pause an agent
node scripts/agent.js pause --id <agent_id>

# Delete an agent
node scripts/agent.js delete --id <agent_id>

🔗 MCP Server Integration

Connect your agent to external tools:

const agent = await client.createAgent({
  name: "MCP Agent",
  config: {
    prompt: "You can use tools to help users",
    mcp_servers: [{
      name: "my-tools",
      url: "https://my-server.com/mcp",
      auth_type: "bearer_token",
      auth_token: "secret"
    }]
  }
});

Add custom knowledge to your agent:

# Create agent with knowledge base
node scripts/agent.js create --name "FAQ Bot" --kb-id 123

Made with ❤️ by Nick Gill

README.md

No README available.

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

  • OpenClaw CLI installed and configured.
  • Language: Markdown
  • License: MIT
  • Topics:

Configuration

| Parameter | Default | Description | |------------------------|---------|--------------------------------------| | llm_model | gemini-2.5-flash-lite | LLM model for responses | | llm_temperature | 0.7 | Response creativity (0-2) | | max_call_duration | 900 | Max call length in seconds | | allow_interruptions | true | Let users interrupt agent | | auto_noise_reduction | true | Filter background noise |

FAQ

How do I install voice-ai-agents?

Run openclaw add @gizmogremlin/voice-ai-agent in your terminal. This installs voice-ai-agents into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/gizmogremlin/voice-ai-agent. Review commits and README documentation before installing.