Voice Agent Builder

Build and manage Voice AI agents using Vapi, Bland.ai, or Retell. Create agents, configure voices, set prompts, make outbound calls, and retrieve transcripts...

Security Scan

The skill's code, docs, and required VAPI_API_KEY are consistent with a Vapi-focused voice-agent helper; nothing in the files indicates hidden exfiltration or unrelated privileges.

Purpose & Capability

Name/description (build/manage voice agents for Vapi/Bland.ai/Retell) align with the included files and requirements. The only required environment variable is VAPI_API_KEY, which the provided vapi_agent.py uses to call https://api.vapi.ai — this is proportional to the stated purpose.

Instruction Scope

SKILL.md instructs running the included Python CLI which only calls the Vapi API. It does instruct users to pass third-party credentials (e.g., Twilio SID/AuthToken) in JSON payloads when importing numbers — that is expected for phone import but is sensitive. The instructions do not request unrelated files, system config, or hidden endpoints.

Install Mechanism

No install spec; this is instruction-only plus a small Python script. No external downloads or archives are executed or written to disk by an installer, which reduces risk.

Credentials

Only VAPI_API_KEY is declared and used. That is appropriate for a wrapper that controls Vapi resources (agents, calls, transcripts) but is powerful — possession of the key allows creating calls and retrieving transcripts, so users should limit its scope and treat it as sensitive. The skill does not require other unrelated credentials.

Persistence & Privilege

Skill is not always-enabled and uses normal autonomous invocation defaults. It does not modify other skills or system configuration and has no persistent install steps.

Assessment

This skill appears to do what it says: it wraps the Vapi API and needs your VAPI_API_KEY to manage agents and make calls. Before installing, verify you trust the Vapi service and the skill author/site (agxntsix.ai); treat VAPI_API_KEY as highly sensitive (it can create calls and access transcripts). Avoid pasting third-party secrets (Twilio SID/AuthToken, etc.) on shared shells or in command history — pass them securely. Review Vapi account permissions, expected billing for outbound calls, and privacy implications (call transcripts may contain PII). If unsure, run the script in an isolated environment and inspect network traffic to api.vapi.ai.

Build, configure, and manage Voice AI agents. Supports Vapi (primary), Bland.ai, and Retell platforms.

Quick Start

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

# Create a voice agent
python3 {baseDir}/scripts/vapi_agent.py create-agent '{"name":"Sales Agent","firstMessage":"Hi! How can I help you today?","systemPrompt":"You are a helpful sales assistant for Acme Corp."}'

# Make an outbound call
python3 {baseDir}/scripts/vapi_agent.py call '{"assistantId":"asst_xxx","phoneNumberId":"pn_xxx","customer":{"number":"[phone]"}}'

# List agents
python3 {baseDir}/scripts/vapi_agent.py list-agents

# List calls
python3 {baseDir}/scripts/vapi_agent.py list-calls

Platform Comparison

Feature	Vapi	Bland.ai	Retell
Best For	Custom agents, dev-friendly	Simple outbound campaigns	Enterprise, low latency
Latency	~800ms	~500ms	~500ms
Languages	100+	30+	30+
Custom LLM	✅ Any OpenAI-compatible	✅ Limited	✅ Via API
Phone Numbers	Buy/import	Buy/import	Buy/import
Pricing	$0.05/min + provider costs	$0.09/min all-in	$0.07-0.15/min
WebSocket	✅	❌	✅
Knowledge Base	✅ Built-in	✅	✅
Transfers	✅	✅	✅

Recommendation: Start with Vapi — most flexible, best docs, largest community. Use Bland for simple high-volume outbound. Use Retell for enterprise low-latency needs.

See {baseDir}/scripts/voice_comparison.md for detailed breakdown.

Agent Creation Workflow

1. Choose a Voice

Vapi supports multiple TTS providers:

• ElevenLabs — Best quality, most natural (recommended)
• PlayHT — Good quality, lower cost
• Deepgram — Fast, good for real-time
• Azure — Enterprise, many languages

2. Configure the Agent

{
  "name": "Appointment Setter",
  "firstMessage": "Hi! This is Sarah from Dr. Smith's office. I'm calling to help you schedule your appointment.",
  "systemPrompt": "You are Sarah, a friendly appointment scheduler...",
  "voice": {
    "provider": "11labs",
    "voiceId": "21m00Tcm4TlvDq8ikWAM"
  },
  "model": {
    "provider": "openai",
    "model": "gpt-4o",
    "temperature": 0.7
  },
  "endCallFunctionEnabled": true,
  "maxDurationSeconds": 300,
  "silenceTimeoutSeconds": 30
}

3. Prompt Engineering for Voice

Voice prompts differ from text. Key principles:

• Keep responses SHORT — 1-2 sentences max per turn
• Be conversational — use filler words naturally ("Sure thing!", "Got it!")
• Handle interruptions — voice agents get cut off, design for it
• Confirm understanding — repeat back key info (names, numbers, dates)
• Include fallback — "I didn't catch that, could you repeat?"

4. Phone Number Setup

# List available phone numbers
python3 {baseDir}/scripts/vapi_agent.py list-phones

# Buy a number (via Vapi dashboard or API)
# Import existing number (Twilio, Vonage)
python3 {baseDir}/scripts/vapi_agent.py import-phone '{"provider":"twilio","number":"[phone]","twilioAccountSid":"AC...","twilioAuthToken":"..."}'

5. Call Handling

Outbound calls:

python3 {baseDir}/scripts/vapi_agent.py call '{"assistantId":"asst_xxx","phoneNumberId":"pn_xxx","customer":{"number":"[phone]"}}'

Inbound: Assign agent to phone number in Vapi dashboard, or via API:

python3 {baseDir}/scripts/vapi_agent.py update-phone '{"id":"pn_xxx","assistantId":"asst_xxx"}'

Integration Patterns

Voice + CRM (GHL)

1. Voice agent qualifies lead on call
2. Use Vapi's serverUrl webhook to capture call data
3. On call end → create/update GHL contact
4. Move opportunity to appropriate pipeline stage
5. Schedule follow-up if needed

Voice + Calendar Booking

1. Agent checks availability via calendar API
2. Uses function calling to book appointment
3. Confirms date/time verbally
4. Sends SMS confirmation after call

Voice + Knowledge Base

Upload documents to Vapi's knowledge base for RAG:

python3 {baseDir}/scripts/vapi_agent.py create-kb '{"name":"Product FAQ","files":["faq.pdf"]}'

Available Commands

python3 {baseDir}/scripts/vapi_agent.py create-agent '{...}'     # Create new agent
python3 {baseDir}/scripts/vapi_agent.py get-agent <id>            # Get agent details
python3 {baseDir}/scripts/vapi_agent.py list-agents               # List all agents
python3 {baseDir}/scripts/vapi_agent.py update-agent <id> '{...}' # Update agent
python3 {baseDir}/scripts/vapi_agent.py delete-agent <id>         # Delete agent
python3 {baseDir}/scripts/vapi_agent.py call '{...}'              # Make outbound call
python3 {baseDir}/scripts/vapi_agent.py get-call <id>             # Get call details
python3 {baseDir}/scripts/vapi_agent.py list-calls                # List all calls
python3 {baseDir}/scripts/vapi_agent.py list-phones               # List phone numbers
python3 {baseDir}/scripts/vapi_agent.py import-phone '{...}'      # Import phone number
python3 {baseDir}/scripts/vapi_agent.py update-phone '{...}'      # Update phone config

Credits

Built by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.

📅 Need help setting up OpenClaw for your business? Book a free consultation