Voice Agent Builder for Openclaw

A comprehensive toolkit for building, configuring, and managing AI-powered voice agents across multiple telephony providers.

aiwithabidi
v1.0.0
Mar 7, 2026
0
313
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install voice-agent-builder

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install voice-agent-builder 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 Agent Builder?

The Voice Agent Builder is a versatile toolset designed to simplify the deployment of AI-driven voice assistants. It serves as a bridge between powerful LLMs and voice platforms like Vapi, Bland.ai, and Retell. By integrating this into your Openclaw Skills library, you can programmatically manage agent personalities, select high-quality TTS providers like ElevenLabs, and automate complex telephony workflows.

This skill is particularly valuable for developers looking to build low-latency voice applications that can handle natural conversation nuances. It abstracts the complexities of different provider APIs into a unified set of CLI commands, allowing for rapid prototyping and scaling of voice-first automation strategies.

Voice Agent Builder Use Cases

  • Building automated appointment setters and reminders
  • Creating sophisticated IVR systems for customer support
  • Executing high-volume outbound lead qualification calls
  • Implementing voice-based RAG for querying documentation over the phone
  • Integrating voice interactions with CRMs for real-time lead updates

How Voice Agent Builder Works

  1. Set up the environment with required API keys such as the VAPI_API_KEY.
  2. Define the agent configuration, including voice identity, model parameters (like GPT-4o), and specific system prompts.
  3. Provision or import phone numbers to the platform using the provided CLI scripts.
  4. Launch outbound calls or configure inbound handlers to initiate the voice AI interaction.
  5. Capture transcripts and call data for integration with external databases or workflow automation tools.

Voice Agent Builder Setup

To begin using this skill, ensure you have Python 3.10+ installed and set your environment variables:

export VAPI_API_KEY="your-vapi-api-key"

You can then interact with the agent scripts directly:

# Create an agent
python3 scripts/vapi_agent.py create-agent '{"name":"Agent Name", "voice": {"provider": "11labs"}}'

# Initiate a call
python3 scripts/vapi_agent.py call '{"assistantId":"id", "customer":{"number":"+15551234567"}}'

Voice Agent Builder Data Schema & Taxonomy

The system manages data across several key entities to ensure consistent voice performance:

Component Details
Agent Profile Contains the system prompt, first message, and voice provider settings.
Call Logs Includes data on duration, cost, recording URLs, and conversation transcripts.
Phone Config Maps specific phone numbers to assistant IDs for inbound call routing.
Knowledge Base Stores uploaded files (PDF/Text) used for RAG during voice sessions.

Voice Agent Builder Advanced Features

  • Support for multiple TTS providers including ElevenLabs, PlayHT, and Deepgram
  • Built-in platform comparison to choose between Vapi, Bland.ai, and Retell based on latency and cost
  • Advanced function calling capabilities for real-time external API interactions during calls
  • Native Knowledge Base integration for context-aware RAG voice responses
  • Seamless webhook support for CRM and ERP automation hooks using Openclaw Skills architecture

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Github Stars: 0
forks: 0

Featured*