Customer support decision

8call

A single competent developer can build a useful, smaller 8call replacement by wiring telephony + STT/TTS + an LLM and a simple DB-backed UI; existing open-source projects (microsoft/call-center-ai) cover the core technical flows.

Visit website

Built by Michael, who ships 5 products in this index

You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off160 h to build

$150/mo6 h/mo upkeep

No published price to break even against.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All 8call alternatives, with the arithmetic →

What a replacement has to do

  • Receive inbound call → transcribe speech → run intent/response model → synthesize reply and place outbound audio → log call and metadata

What it still won’t have

  • Hosted SLA, monitoring and uptime guarantees
  • Proprietary integrations and prebuilt connectors to CRMs or business tools
  • Polished UX, onboarding, and support
  • Potential economy of scale on telephony and model usage discounts

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

8call does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a minimal self-hosted AI call-agent using Node.js (or Python) + Postgres + simple React admin UI. Core features in scope: receive and route PSTN calls via Twilio, record and stream audio to a speech-to-text API, call an LLM API for intent and response generation, synthesize reply audio (TTS) and play back to caller, store call recordings and transcripts in Postgres, and expose a web UI for searching call logs and listening to recordings. Out of scope: multi-tenant billing, advanced CRM integrations, and analytics dashboards. Include retry/error handling for telephony and ML API calls, basic authentication for the UI, containerized deployment (Docker), and unit/integration tests for the telephony, STT, LLM, and TTS flows.
How we checked2 sources · 2/3 runs agreed · evidence score 58

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 2 cited sources+1
  • Evidence score58

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded