Home services

Booking calls where the address and the time window are right the first time.

A repair booking is only as good as the details behind it: the address, the problem, the time window, the number to call back. VoiceLens grades each as a slot, flags corrections that did not stick and catches the dead air that makes callers hang up and call a competitor.

Free to start · Works with any call platform · Same rubric for bots and people

How VoiceLens helps

From transcript to a scorecard your team acts on.

The booking as a slot list

Model the details every booking needs as slots and see, per call, which were volunteered, which were asked for and which were corrected.

Dead air and repetition caught

Long silences and repeated questions are graded as faults with timestamps, so you can fix the prompt or the process behind them.

Channels per line or per bot

Each phone line or AI receptionist gets its own channel and ingest token, so quality is compared per source and not blurred together.

Fault detection

What VoiceLens catches on these calls

Every fault is timestamped and pinned to the transcript turn it came from, for AI and human agents alike.

  • Customer had to prompt

    The caller has to nudge the agent to continue or respond.

  • Missed correction

    The caller corrects a detail and the agent keeps the old one.

  • Dead air

    Silence long enough for the caller to wonder if anyone is there.

  • Question repetition

    The agent asks for something the caller already gave.

See what your QA process has been missing.

Create a workspace, drop in a recording or a transcript, and read the first scorecard in minutes.