Call screening API: know the caller before you answer

One lookup while the phone rings tells your stack who's calling and whether to answer, greet by name, or drop. Built for Voice AI agents, UCaaS and support teams.

Your AI answers every call. That's the problem.

A spam call to a voice agent isn't free: it burns speech-to-text, LLM tokens, telephony minutes and a concurrency slot on a caller who was never a customer. Robocall campaigns multiply that by thousands.

Screening happens before the pickup, so the meter never starts. For heavier abuse, pair it with the spam call blocking API and drop repeat offenders outright.

One unscreened spam call

  • Speech-to-text + LLM tokens wasted
  • Telephony minutes wasted
  • Concurrency slot blocked
  • Screening lookup instead one GET

Screening rules you write yourself

The API returns facts, not opinions. Your routing logic stays yours, in your stack.

if spam_score > 80 → drop

Known spammers and robocallers never reach an agent, human or AI.

if reputation == VERIFIED → greet by name

Business identity from 195 countries lets your agent open with context instead of an interrogation.

if entity == UNKNOWN → voicemail

Unknowns get a softer path: voicemail, callback flows or extra verification before a human's time is spent.

Works through the native Asterisk module, Aircall, Dialpad and GoHighLevel integrations, or plain REST from any bot framework. Outbound teams can also run a caller ID test to check their own numbers.

Call screening API questions

Screen your next call

Plans from $25/month. Voice AI platform with real volume? Let's talk numbers.