Rogervoice's automatic captions arrive faster in FCC lab tests

In the FCC's test lab, Rogervoice's automatic captions arrived in 1.2 to 1.3 seconds, against 1.8 to 2.4 for other providers. Its word error rates were higher but comparable.

  • Not rated a person

    The FCC certified the app on lab tests before it captioned users' calls in the United States, and its later notices report no outcome for users.

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

Aggregate average caption delay of other IP CTS providers on the same two call scenarios. Measured.

Without the system
1.8 to 2.4 seconds
With it
1.2 to 1.3 seconds
The system’s part
The National Test Lab measured the app's automatic captions against other providers' results on the same call scenarios, which isolates the recognizer's output. The FCC does not say which captioning mode produced the other providers' results. It does not name the engine or show that it learns from data.
Later
Persisted, 13 July 2026. The FCC extended Rogervoice's conditional certification through 13 January 2027 to keep service to consumers running while it reviews the application for full certification.
Not yet checked
LimitsCosts and harmsLearns from data

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
Rogervoice ASR-only Internet Protocol Captioned Telephone Service (IP CTS) app
Made by
Rogervoice SAS (the FCC does not name the speech recognition engine)
Used by
Rogervoice SAS
Where
United States
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Documenting/Recording Information
Collections
Scrutiny and findings, Cross-border records
Last revised
1 November 2026

Sources

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

    Federal Communications Commission, Consumer and Governmental Affairs Bureau. Order, DA 24-48, CG Docket No. 03-123 (conditional certification of Rogervoice to provide IP CTS on a fully automatic basis). Adopted and released 17 January 2024. Paragraph 9, a sentence split by a page break.

    call scenarios ranged from 1.2 to 1.3 seconds, compared to an aggregate average of 1.8 to 2.4 seconds for other IP CTS providers.

  2. Regulatory document, by authors with no tie to the system. Context or contrary evidence.

    Federal Communications Commission, Consumer and Governmental Affairs Bureau. Public Notice, DA 26-728, CG Docket No. 03-123: Extension of Conditional Certification of Rogervoice SAS, to Provide Internet Protocol Captioned Telephone Service. Released 13 July 2026.

    To ensure uninterrupted service to consumers pending Bureau review, Rogervoice's current conditional certification to provide IP CTS is extended for six months, through January 13, 2027.

Details

AI system

Workflow

Automatic speech recognition captioned every call, with no communications assistant. The service ran as an app on users' own Android or iOS devices. Rogervoice's servers were cloud-based, and its provider had to keep redundancy and backup power.

Follow-up

Conditions for replication

Neither Rogervoice nor any vendor may store call transcriptions or recordings after a call. The service must meet the FCC's minimum standards in actual operation.

Entry details

Sector

Telecommunications relay services / accessibility for people with hearing loss.

Purpose

Rogervoice built its app to caption phone calls for people with hearing loss with automatic speech recognition alone.

30 more questions 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). Rogervoice's automatic captions arrive faster in FCC lab tests (AIBD-1002). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1002.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions