# How Speak uses Labelbox

**nearly 50%**: “Speak's signal-production time was cut by nearly 50%”

As published on [labelbox.com](https://labelbox.com/customers/speak-customer-story/). Captured by usedby on 2026-10-07.

- Company: [Speak](https://www.usedby.ai/companies/speak.md)
- Tool: [Labelbox](https://www.usedby.ai/tools/labelbox.md)

## What the story says

Speak, a language learning app, uses Labelbox to produce expert-graded signal that trains and evaluates its speech recognition and LLM-based tutoring models. It runs an automatic labeling loop that evaluates its speech systems daily on production data and retrains the models.

Summary written by usedby from the source page, in English. The figures are those of Labelbox and Speak, not ours.

> Increased efficiency: Speak's signal-production time was cut by nearly 50%, allowing it to release new features and languages at a faster pace.

- **35%**: “we saw model accuracy improvements of 35% after using Labelbox”
- **2x**: “what effectively translated into a 2x increase in speed in terms of accelerating model development”

> 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.
>
> Tobi Szuts, Machine Learning Engineer at Speak

## What usedby checked

We compared the story with its live page on 2026-10-07.

- Checked: the figure nearly 50% is printed word for word on the page, near the name of Speak.
- Checked: the passage quoted above is copied word for word from the page, near the name of Speak.
- Checked: Speak uses Labelbox. Confirmed line. Latest check across sources: 2026-10-07.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/speak-labelbox · How we check: https://www.usedby.ai/methodology