Cartesia vs Deepgram
Cartesia is ahead on both datasets together and the Pipecat Dataset, and Deepgram on time to first text and final-text delay. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
Each row sets Cartesia's best model against Deepgram's best on that measure.
- Overall WER2.63%Cartesia Ink 23.78%Deepgram Nova-3
- Pipecat Dataset WER2.39%Cartesia Ink 23.46%Deepgram Nova-3
- Ocular Dataset WER3.09%Cartesia Ink 24.18%Deepgram Flux English
- Time to first text1.51sCartesia Ink 2791msDeepgram Flux English
- Final-text delay123msCartesia Ink 2103msDeepgram Nova-3
Cartesia vs Deepgram FAQ
Is Cartesia or Deepgram better for speech-to-text?
Cartesia is ahead, 1.08 points lower. The best Cartesia result is Cartesia Ink 2 at 2.39%, and the best Deepgram result is Deepgram Nova-3 at 3.46%, on the Pipecat Dataset.
Cartesia is ahead, 1.08 points lower. The best Cartesia result is Cartesia Ink 2 at 2.39%, and the best Deepgram result is Deepgram Nova-3 at 3.46%, on the Pipecat Dataset.
Deepgram is faster, 20ms sooner. The best Cartesia result is Cartesia Ink 2 at 123ms, and the best Deepgram result is Deepgram Nova-3 at 103ms, on final-text delay.
Cartesia: Cartesia Ink 2. Deepgram: Deepgram Flux English, Deepgram Flux Multilingual, Deepgram Nova-3. Every model ran the same tests on Converse-STT.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.