CaptionMate wins on speed and on four of five accuracy tests

In the FCC's lab tests, Clarity's automatic CaptionMate captions arrived in 1.1 to 1.6 seconds, against 4.8 to 6.9 for assisted providers. They had fewer errors in four of five scenarios.

  • Not rated a person

    The FCC certified the service on lab tests and beta comments, and no outcome for users in service is reported.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Average error rates of CA-assisted providers on the same call scenarios. Measured.

Without the system
8.9% to 19.5%
With it
6.3% to 35.9% (Clarity's median error rates), lower in four of five scenarios
The system’s part
The National Test Lab measured the automatic captions against those of human-assisted providers on the same call scenarios, which isolates the recognizer's output. The FCC does not describe the recognizer or show that it learns from data.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
CaptionMate, Clarity's ASR-only Internet Protocol Captioned Telephone Service (IP CTS) app
Made by
Clarity Products, LLC
Used by
Clarity Products, LLC
Where
United States
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Documenting/Recording Information
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Federal Communications Commission, Consumer and Governmental Affairs Bureau. Memorandum Opinion and Order, DA 20-587, CG Docket No. 03-123 (conditional certification of Clarity Products, LLC to provide IP CTS using only automatic speech recognition). Adopted and released 4 June 2020.

    Clarity’s median caption delays for various call scenarios ranged from 1.1 to 1.6 seconds, while CA-assisted providers’ average of the median caption delays were significantly longer, ranging from 4.8 to 6.9 seconds.

Details

AI system

Workflow

Call audio went over a SIP trunk to middleware that used cloud services to transcribe it. Captions went to the CaptionMate app on a phone or tablet or to a website.

Follow-up

Conditions for replication

Clarity must show in actual operation that the service meets the FCC's standards. Neither Clarity nor its vendor may keep call content after the call.

Entry details

Sector

Telecommunications relay services / accessibility for people with hearing loss.

Purpose

Clarity Products built CaptionMate to caption both sides of phone calls for people with hearing loss with automatic speech recognition alone.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). CaptionMate wins on speed and on four of five accuracy tests (AIBD-0822). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0822.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions