AssemblyAI is ahead of Google on both datasets together, time to first text and final-text delay. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Each row sets AssemblyAI's best model against Google's best on that measure. For costs, see our breakdown of AssemblyAI pricing.
It is too close to call: the gap is inside the margin of error. The best AssemblyAI result is AssemblyAI STT 3.7 Realtime Agent at 1.68%, and the best Google result is Google Chirp 3 at 2.00%, on the Pipecat Dataset.
It is too close to call: the gap is inside the margin of error. The best AssemblyAI result is AssemblyAI STT 3.7 Realtime Agent at 1.68%, and the best Google result is Google Chirp 3 at 2.00%, on the Pipecat Dataset.
AssemblyAI is faster, 428ms sooner. The best AssemblyAI result is AssemblyAI STT 3.7 Realtime Agent at 47ms, and the best Google result is Google Chirp 3 at 475ms, on final-text delay.
AssemblyAI: AssemblyAI STT 3.7 Realtime Agent, AssemblyAI Universal 3.5 Pro, AssemblyAI Universal 3.6 Pro. Google: Google Chirp 2, Google Chirp 3. Every model ran the same tests on Converse-STT.
Cekura runs these simulated calls on your agent and scores every one.