2 days
time to implement
As published on assemblyai.com. Captured by usedby on Oct 8, 2026.
What happened
Dexa uses AssemblyAI to transcribe podcasts at scale with speaker identification, and to detect chapters in episodes. This powers an interactive knowledge base where users ask questions and are taken to the relevant moment or chapter in a podcast.
Summary written by usedby from the source page, in English. The figures are those of Assembly AI and Dexa, not ours.
Since implementation, Dexa has processed millions of hours of podcast content without interruption. This consistent performance at scale demonstrates the API's reliability and Dexa's success in making podcast knowledge more accessible.
Assembly has done a fantastic job with transcriptions at scale. It's accurate, fast, and reliable.
What the story claims, and what we checked
We compared the story with its live page on Oct 8, 2026.
- The figure: 2 daysCheckedThe figure is on the page; its label is our wording.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Dexa.
- Dexa uses Assembly AICheckedConfirmed line. Latest check across sources: Oct 8, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.




