pamela-call

13
1
Source

Make AI-powered phone calls with Pamela's voice API. Create outbound calls, register custom tools for mid-call actions, handle webhooks, and build React UIs. Use when the user wants to make phone calls, integrate voice AI, build IVR systems, navigate phone menus, or automate phone tasks.

Install

mkdir -p .claude/skills/pamela-call && curl -L -o skill.zip "https://mcp.directory/api/skills/download/6493" && unzip -o skill.zip -d .claude/skills/pamela-call && rm skill.zip

Installs to .claude/skills/pamela-call

About this skill

Pamela Calls

Make AI phone calls instantly. No lag, no setup, unlimited scale. ThisIsPamela is a voice AI platform for outbound calls, phone tree navigation, and integration via SDKs, webhooks, and MCP.

Jump to: Installation · Quick Start · Examples · SDK Reference

ClawHub skill release: v1.1.12

Prerequisites

  • API subscription (required for API access)
  • API key from your API account
  • Node.js 18+, Bun, or Python 3.8+ (for Python)

Installation

JavaScript/TypeScript: (npm, yarn, or bun)

npm install @thisispamela/sdk
# or: yarn add @thisispamela/sdk
# or: bun add @thisispamela/sdk

Python:

pip install thisispamela

React: (npm, yarn, or bun)

npm install @thisispamela/react @thisispamela/sdk
# or: bun add @thisispamela/react @thisispamela/sdk

CLI:

npm install -g @thisispamela/cli

MCP (for MCP-based agents):

npm install @thisispamela/mcp

Widget (embeddable, no framework):

npm install @thisispamela/widget

Latest versions: SDK / CLI / Widget / MCP / Python / React 1.2.0.

Getting Your API Key

  1. Sign up for an API subscription at developer.thisispamela.com
  2. Navigate to Settings → API Access
  3. Set up billing through Stripe
  4. Click "Create API Key"
  5. Save immediately - the full key (starts with pk_live_) is only shown once

Trust & security

  • Official packages: npm @thisispamela, PyPI thisispamela — verify these exact names to avoid typosquatting.
  • Before going live: Use a restricted or test API key when trying the skill; enable billing alerts in your account; do not put production keys (pk_live_...) in public configs or logs.
  • Webhooks: Always validate the X-Pamela-Signature header and secure your endpoint; see SDK docs for verification.
  • Data: Call audio and transcripts are sent to Pamela and may be stored or forwarded to your webhooks; review privacy and data practices (or contact [email protected]).
  • Costs: Monitor usage and billing after enabling; only connected minutes are charged at $0.10/min.

Quick Start

Note: Phone numbers must be in E.164 format (e.g., +1234567890).

JavaScript

import { PamelaClient } from '@thisispamela/sdk';

const client = new PamelaClient({ apiKey: 'pk_live_...' });

const call = await client.createCall({
  to: '+1234567890',
  task: 'Call the pharmacy and check if my prescription is ready',
  voice: 'female',
  agent_name: 'Pamela',
});

const status = await client.getCall(call.id);
console.log(status.transcript);

Python

from pamela import PamelaClient

client = PamelaClient(api_key="pk_live_...")

call = client.create_call(
    to="+1234567890",
    task="Call the pharmacy and check if my prescription is ready",
    voice="female",
    agent_name="Pamela",
)

status = client.get_call(call["id"])
print(status["transcript"])

CLI

export PAMELA_API_KEY="pk_live_..."

thisispamela create-call \
  --to "+1234567890" \
  --task "Call the pharmacy and check if my prescription is ready"

Examples

ScenarioExample Task
Appointment Scheduling"Call the dentist and schedule a cleaning for next week"
Order Status"Call the pharmacy and check if my prescription is ready"
Customer Support"Navigate the IVR menu to reach billing department"
Information Gathering"Call the restaurant and ask about vegetarian options"
Follow-ups"Call to confirm the appointment for tomorrow at 2pm"
IVR Navigation"Navigate the phone menu to reach a human representative"

Key Features

  • Phone tree navigation - Automatically navigates IVR menus, handles holds and transfers
  • Custom tools - Register tools the AI can call mid-conversation
  • Real-time transcripts - Webhook updates as the call progresses
  • React components - Pre-built UI for call status and transcripts

SDK Reference

For detailed SDK documentation:

Webhooks

Pamela sends webhooks for call lifecycle events:

  • call.queued - Call created and queued
  • call.started - Call connected
  • call.completed - Call finished successfully
  • call.failed - Call failed
  • call.transcript_update - New transcript entries

Only credential required is your API key. For webhooks, always verify the X-Pamela-Signature header; see SDK docs for verification.

Billing

  • $0.10/minute for API usage
  • Minimum 1 minute per call
  • Only connected calls are billed
  • API subscription required

Troubleshooting

"Invalid API key"

  • Verify key starts with pk_live_
  • Check key is active in the API settings panel

"403 Forbidden"

  • API subscription required
  • Check subscription status at developer.thisispamela.com

"Invalid phone number"

  • Use E.164 format with country code: +1234567890

Resources

terabox-link-extractor

openclaw

Direct link extraction from TeraBox URLs using the XAPIverse protocol. Extracts high-speed download and stream links (360p/480p) without browser session requirements. Use when the user provides a TeraBox link and wants to download or stream content directly.

27502

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

615420

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

838363

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

90174

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

479132

dokploy

openclaw

Manage Dokploy deployments, projects, applications, and domains via the Dokploy API.

285101

You might also like

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

2,2643,720

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

3,6493,329

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

4,6862,231

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,2841,724

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,4861,552

youtube-transcribe-skill

feiskyer

Extract subtitles/transcripts from a YouTube video URL and save as a local file. Use when you need to extract subtitles from a YouTube video.

3671,372