Skip to main content
usedby
Search tools, companies

How Gradient Labs uses Deepgram

300ms+

“300ms+ reduction in end-to-end transcription latency”

As published on deepgram.com. Checked by usedby on Oct 9, 2026.

What happened

Gradient Labs builds AI voice support agents for regulated financial institutions and uses Deepgram Nova-3 as the primary real-time speech-to-text engine in a multi-provider transcription pipeline. It also uses Deepgram's EU hosting endpoints to keep processing local.

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

300ms+ Latency Reduction: By prioritizing Deepgram's results and moving to EU hosting, end-to-end latency dropped significantly, making conversations feel immediate and engaging.

From the page. deepgram.com

What the story claims, and what we checked

What we compared with the page.

  • The figure: 300ms+CheckedPrinted word for word on the page, near the name of Gradient Labs.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of Gradient Labs.
  • Gradient Labs uses DeepgramCheckedConfirmed line.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

30%“the time spent per audit has been reduced by 30%”Abby Connect uses Deepgram. Another customer of Deepgram58%“measured a shocking 58% reduction in transcription latency”BIGVU uses Deepgram. Another customer of Deepgram10%“produced a 10% increase in recovery rates and smarter workforce deployment”Creditas uses Deepgram. Another customer of Deepgram