Skip to main content

[verdict][curated prompt][source: thrumble.ai]

Can I vibecode Thrumble?

// buildable in a weekend, but real gaps stay open

A single inbound receptionist agent is a credible weekend build with LiveKit Agents or Pipecat plus a SIP trunk. Thrumble as a product is larger: agent config UI, knowledge bases, tools, call transfer, outbound campaigns, phone numbers, transcripts, and production telephony. You can DIY the core conversation loop; you still own carriers, media ports, failed calls, and ops.

confidence: high

what it is: Voice AI platform for inbound and outbound business phone calls

Buildability index · an editorial game

  • Price 99 $/month weight: plus 3
  • Time weekend for one inbound agent; ongoing for campaigns and production ops weight: plus 2
  • Category voice ai no weight
  • Moat infrastructure scale · integrations weight: minus 3
  • Confidence high weight: plus 1
  • What you lose 5 items weight: minus 2
  • Site thrumble.ai (si apre in una nuova scheda) no weight
Indice: plus 1. a toss-up

They cancel out. This is where it comes down to how much the subscription annoys you.

Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.

What you build

Answer one inbound number with a realtime STT → LLM → TTS agent, look something up, and log the call outcome.

what you need

  • public VM with TLS and correctly opened SIP / WebRTC / RTP ports
  • SIP trunk and phone number (e.g. Telnyx)
  • STT, LLM, and TTS API keys
  • consent and recording rules for your country before real traffic

Productized call-centre SaaS; the DIY slice is one inbound agent, not the full platform.

The prompt

A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.

One-shot prompt EN
Build me a focused self-hosted alternative to Thrumble for one inbound business number.
Requirements:

- Python 3.12 + livekit-agents with one AgentServer worker.
  Direct provider plugins only · no managed agent host.
- Docker Compose: LiveKit Server, Redis, LiveKit SIP, Caddy for HTTPS/WSS.
  Expose only documented SIP and UDP media ports.
- One Telnyx DID + credential SIP trunk. Checked-in inbound-trunk and
  dispatch-rule JSON that routes calls to receptionist-agent.
- AgentSession: Silero VAD, Deepgram STT, gpt-4.1-mini (OpenAI plugin),
  Cartesia TTS. Secrets only from .env.
- Narrow receptionist prompt: answer FAQs from a local knowledge.md,
  book a callback into SQLite after confirmation, transfer is out of scope.
- Persist call id, timestamps, transcript, and outcome to SQLite.
  JSON logs + /healthz. Recording off by default.
- Unit tests for FAQ lookup and callback confirmation; scripted agent tests
  for interruption and refusal to invent facts.
- make setup / make dev / make smoke + docker compose up -d.
  Smoke test must pass in the LiveKit agent console before a real PSTN call.
- README: DNS, TLS, firewall, Telnyx, trunk, keys, test-call steps,
  and common one-way-audio / SIP auth failures.
- Out of scope: outbound campaigns, multi-tenant dashboard, knowledge-base
  crawler, tool marketplace, call transfer, billing, HA, compliance claims.

Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.

What you lose

  • hosted agent builder, knowledge bases, tools, and transfer destinations
  • outbound campaign dialer and contact workflows
  • managed phone numbers, concurrency, and telephony debugging
  • call logs, recordings, post-call extraction, and analytics
  • uptime, support, and multi-tenant workspace polish

Why people still pay

They pay to go from a demo voice loop to dependable inbound and outbound calling without running SIP, media, agent workers, numbers, campaigns, and monitoring themselves.

moat: Infrastructure scale Integrations what a moat is

realtime telephony ops plus business control plane (KB, tools, campaigns)

Who has already built it

Starting from here is still vibecoding: the prompt is for when you want it exactly your way.

Do you agree?

The vote balance

Ancora nessun voto: il tuo è il primo.

Nessun voto ancora — il primo pesa.

Related apps

From a Confusing Brief to a Complete UX/UI A vague brief becomes a navigable app. Product Ad From a Single Photo A photo becomes an animated ad, no code required. Get Claude to Watch Your Videos Claude watches your videos and turns them into text. Higgsfield Inside Claude Code Generate images and video while you code in Claude Code. Turn a Loom Recording Into a Web Page A screen recording becomes a web page, no code. Vertical Shorts With NotebookLM Your sources become a vertical short. Luxury Landing Pages on Lovable A luxury landing page from a single prompt. Excalidraw Running Locally Excalidraw free on your computer, no code. Mistral OCR in Your Workflow Extract text from documents with Mistral OCR. Claude SEO in the Terminal 25 free SEO skills inside Claude Code. Google Search Console inside Claude Code Search Console data inside your terminal. Claude Code Routines Claude working on its own, computer off. Clone a Landing Page in React With v0 Clone a real landing page into React code. Context Economy With Claude Work light and don't burn through Claude's limits. From Prompt to Self-Improving Skill Claude skills that learn from your mistakes. From NotebookLM to Canva: Presentations NotebookLM slides, finally editable in Canva. The Map for Understanding Every AI Tool 12 categories for placing any AI tool. Transparent PNGs With ChatGPT Real transparency, not a fake checkerboard. Animated Infographics With Gemini Infographics that loop, animated with Gemini. Market Research With Deep Research Deep Research as your market analyst. Get Cited by AI Search Engines (AEO) Become a source that ChatGPT and Perplexity cite.