New tool2026-10-19via GitHubVoice & Text-to-Speech

Lampline

Name: Lampline
Author: C4rohan (GitHub)

Lampline is an open-source, self-hosted platform for building and running AI phone agents: it imports Dialogflow CX and CX Agent Studio agents, has a drag-and-drop builder and test console, connects to Twilio, Telnyx or SIP, and can phone any voice agent with an AI test caller and grade the call.

Visit Lampline ↗

Free (open source)Apache-2.0Python (3.11+ for the native engine); Docker with Compose v2★ 164 (as of 2026-10-23)by C4rohan (GitHub)

Why it matters

For businesses running phone bots on Google's Dialogflow or paying per-minute hosted voice platforms, it offers a way to move agents onto their own hardware and test changes with simulated callers before customers hear them.

Highlights

Imports Dialogflow CX packages and CX Agent Studio apps (flows, pages, forms, playbooks and tools) into an editable builder, and can export agents back to Google's formats.
The Evals tab calls any voice agent with a phone number, including Vapi, Retell or an IVR, plays the caller with an AI test caller, and grades the transcript check by check with reasons.
A free mode runs everything locally (Qwen3 4B in Ollama, Moonshine for listening, Kokoro for speech) with no API keys, after about a 3 GB first download.
Works with about 20 model providers including Claude, OpenAI, Gemini, Bedrock and Ollama, and handles calls over Twilio, Telnyx or a SIP trunk through jambonz.
The README estimates about $0.02-0.17 a call with your own keys, versus $0.50 it cites for hosted alternatives.unverified

Taken from the project's own README, docs or launch page. Claims about speed or accuracy are the maker's unless stated otherwise.

Try it if: You run a phone bot for bookings or support and want to test every change with realistic callers before going live.

Worth knowing: Created October 19, 2026, so it is very new. Per-call cost figures are the project's own estimates. The README says to only call agents you own or are allowed to test, and Google Voice test calls must be dialed by hand.

Quick facts

Pricing	Free (open source); model, speech and telephony providers billed separately if you use them
Free or paid	Free (open source)
License	Apache-2.0
Language	Python (3.11+ for the native engine); Docker with Compose v2
Platform	Local or on-prem via Docker or native engine; Google Cloud deploy listed as coming soon
GitHub stars	★ 164 (as of 2026-10-23)
Maker	C4rohan (GitHub)

Related ranking

See how established tools compare in Best Voice & Text-to-Speech. New releases aren't scored until we review them against the rubric.

What we couldn't verify

highlights[4] (per-call cost estimates are the project's)

Checked 2026-10-23 from the tool's own pages. Prices and star counts change, so confirm on the official site. Listing here is not a ranking or an endorsement.