The use case: how Klubi deploys Deepgram
Klubi uses Deepgram's Nova-3 streaming speech-to-text to power AI voice agents that handle pre-sales outreach, qualification and handoff for its digital group purchasing (consórcio) product in Brazil. The transcription layer also supports service and post-sales workflows, with transcripts feeding monitoring and QA processes.
More reported results
Figures published in Deepgram’s case study. They are not independently measured by usedby.
~80k total monthly customer interactions across pre-sales, post-sales, and support
~30k monthly AI-led voice interactions
In the customer’s words
We evaluated several speech-to-text providers, but Deepgram stood out immediately for Brazilian Portuguese. Other solutions struggled with domain-specific vocabulary—confusing car model names like 'Ônix' with common words like 'ônibus' [bus]. Deepgram got it right, even in noisy environments like traffic or subway calls. That accuracy was non-negotiable for us.Deepgram users in Fintech & Payments
Companies in the same sector, with public evidence.
See all Deepgram customersGo straight to the source
Based on Deepgram’s published case study. We check the public evidence; the results are reported by the vendor.
deepgram.com- Last checked
- Nov 5, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 90%+Checked
Printed word for word on the page, near the name of Klubi.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Klubi.
- Klubi uses DeepgramChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Klubi rebuilt its funnel around AI voice, anchored by Deepgram Speech-to-Text (STT), to increase conversion, expand coverage, and improve consistency across thousands of interactions.



