Deepgram vs Speechmatics
Deepgram is ahead on time to first text and final-text delay, and Speechmatics on both datasets together and the Pipecat Dataset. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
Each row sets Deepgram's best model against Speechmatics's best on that measure.
- Overall WER3.78%Deepgram Nova-32.97%Speechmatics Linden
- Pipecat Dataset WER3.46%Deepgram Nova-32.46%Speechmatics Linden
- Ocular Dataset WER4.18%Deepgram Flux English3.93%Speechmatics Linden
- Time to first text791msDeepgram Flux English1.19sSpeechmatics Linden
- Final-text delay103msDeepgram Nova-3147msSpeechmatics Linden
Deepgram vs Speechmatics FAQ
Is Deepgram or Speechmatics better for speech-to-text?
Speechmatics is ahead, 1.01 points lower. The best Deepgram result is Deepgram Nova-3 at 3.46%, and the best Speechmatics result is Speechmatics Linden at 2.46%, on the Pipecat Dataset.
Speechmatics is ahead, 1.01 points lower. The best Deepgram result is Deepgram Nova-3 at 3.46%, and the best Speechmatics result is Speechmatics Linden at 2.46%, on the Pipecat Dataset.
Deepgram is faster, 44ms sooner. The best Deepgram result is Deepgram Nova-3 at 103ms, and the best Speechmatics result is Speechmatics Linden at 147ms, on final-text delay.
Deepgram: Deepgram Flux English, Deepgram Flux Multilingual, Deepgram Nova-3. Speechmatics: Speechmatics Linden. 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.