# How SyncWords uses DeepL

**4x**: “4x higher audience engagement. Subtitled videos are watched to completion four times more often.”

As published on [deepl.com](https://www.deepl.com/en/customer-stories/syncwords), April 2025. Captured by usedby on 2026-10-07.

- Company: [SyncWords](https://www.usedby.ai/companies/syncwords.md)
- Tool: [DeepL](https://www.usedby.ai/tools/deepl.md)

## What the story says

SyncWords, a provider of live and on-demand video captioning, subtitling and voice translation, integrates the DeepL API into its live streaming workflows to deliver real-time translated captions in many languages. It runs the API in a Kubernetes-based environment and uses glossaries to keep terminology consistent.

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

> SyncWords had tested multiple AI translation tools to evaluate their ability to handle linguistic nuances, industry-specific jargon, and contextual subtleties, before integrating DeepL into its workflow.

- **4-8**: “Traditional live captioning and subtitling systems lagged behind by 4-8 seconds, making real-time engagement frustrating and disconnected.”

> Our customers needed higher-quality translations–especially in European languages–and we had to deliver. That’s why we brought DeepL into our live video workflows. Our clients actually asked us for them.
>
> Giovanni Galvez, VP of Business Development and Strategy

## What usedby checked

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

- Checked: the figure 4x is printed word for word on the page, near the name of SyncWords.
- Checked: the passage quoted above is copied word for word from the page, near the name of SyncWords.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: SyncWords uses DeepL. 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/syncwords-deepl · How we check: https://www.usedby.ai/methodology