The use case: how Speak deploys Labelbox
Speak, a language learning app, uses Labelbox to produce and quality-control the expert-graded data that trains and evaluates its speech recognition and language models. It runs an automatic labeling loop that evaluates its speech systems daily on production data and retrains the models.
More reported results
Figures published in Labelbox’s case study. They are not independently measured by usedby.
we saw model accuracy improvements of 35% after using Labelbox
what effectively translated into a 2x increase in speed in terms of accelerating model development
In the customer’s words
At the highest level, we now have a way to tackle something that used to be very painful—an automatic labeling loop that lets us evaluate our speech systems daily on production data.Other AI tools used by Speak
Other public relationships recorded on usedby.
Explore Speak’s AI stackOther companies using Labelbox
Customers across industries, with public evidence.
AncestryConfirmed
Blue River TechnologyConfirmed
BurberryConfirmed
CAPE AnalyticsConfirmed
CriteoConfirmedGo straight to the source
Based on Labelbox’s published case study. We check the public evidence; the results are reported by the vendor.
labelbox.com- Last checked
- Nov 10, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: nearly 50%Checked
Printed word for word on the page, near the name of Speak.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Speak.
- Speak uses LabelboxChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Speak's signal-production time was cut by nearly 50%, allowing it to release new features and languages at a faster pace.

