Agent builder with tier selection
Describe the job in plain language, choose a voice, and pick Spark, Bolt, or Storm. The platform handles deployment from there.
ThunderPhone is an AI phone agent platform for building, testing, and running production voice agents over real calls and embedded web voice experiences. It supports inbound and outbound calls, web voice widgets, live supervision, and multilingual conversations, with usage-based pricing starting at 2¢/min.
ThunderPhone is an AI phone agent platform for building, testing, and running production voice agents over real calls and embedded web voice experiences. The product is presented as a single stack for setup, deployment, monitoring, and iteration, with both a dashboard workflow and API access.
The platform supports inbound and outbound calling, web voice widgets, testing and simulation, live supervision, and multilingual conversations. Pricing is usage-based, starting at 2 cents per minute, with separate intelligence tiers and no platform fee.
Describe the job in plain language, choose a voice, and pick Spark, Bolt, or Storm. The platform handles deployment from there.
Run text or audio test scenarios before launch, including human-to-AI and AI-to-AI cases, and use the resulting calls as regression tests.
Monitor live and completed calls with analytics, issue grouping, alerts, and the ability to watch calls in progress and whisper guidance mid-conversation.
Connect telephony through native SIP trunking or by importing a VoIP provider, and support inbound, outbound, web, and app-based voice workflows.
Paste a cURL command, OpenAPI spec, or Postman collection to wire integrations automatically, with support for CRMs, calendars, APIs, MCP servers, and knowledge bases.
Use built-in retrieval to ground agents in uploaded documents, then test search and deploy from the same control room.
Answer customer calls with an agent that follows a prompt, uses tools, and hands off to a human when needed.
Run survey, follow-up, reminder, and confirmation calls in bulk, with pacing and retries for outbound campaigns.
Add click-to-talk voice interactions to a website or app without requiring a phone number, using the embeddable widget.
Build agents that are checked with canned scenarios before deployment, so regressions can be caught before customers hear them.
Use live supervision and whisper guidance for production calls where operators need to monitor quality or intervene during a call.
ThunderPhone provides documentation for both dashboard-based setup and API-based setup. The dashboard quickstart walks through creating an agent, setting up billing, adding a phone number, running a simulation, and reviewing the call.
The source pages describe ThunderPhone as a platform for real phone calls, embedded web voice, outbound campaigns, testing, monitoring, and live supervision. It is positioned for production voice agents rather than a single-purpose call widget.
ThunderPhone supports a no-code front end, direct API access, and enterprise deployments. The docs also mention webhooks, a widget component, and integrations with tools such as CRM systems, calendars, APIs, MCP servers, and knowledge bases.
Pricing starts at 2 cents per minute on the Spark tier, with Bolt at 5 cents per minute and Storm at 9 cents per minute. Hold time is billed at a flat 2 cents per minute on every tier, and there is no platform fee.
The source describes HIPAA and GDPR compliance, with BAA and DPA available at no extra charge. The security page also indicates documented compliance practices, but the provided excerpt is partial.
Wallie is an open-source AI streamer that watches your screen, hears chat, and generates live commentary in a configurable persona. It runs locally on your machine with your own keys and is aimed at faceless content, autonomous streams, and real-time reactions.
Claude Overlay is a Windows desktop overlay for Claude Code that reads your screen so you can ask questions, inspect content, and request edits without leaving the current app. It runs on your existing Claude subscription through the Claude CLI, so no separate API key is required.
Trigger.dev chat agent is a durable AI chat backend for developers building stateful conversations that can survive refreshes, crashes, and long-running turns. It connects with the AI SDK `useChat` flow and runs on managed infrastructure with no timeout on a turn.
Flunkey is a voice-first productivity layer for Windows that converts speech into text, AI-assisted outputs, and remembered context. It is built for users who want to capture ideas and actions without leaving the app they are working in.
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.