Gradium vs Smallest Pulse
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Gradium6.48% · 212ms
- Pulse3.66% · 201ms
Smallest Pulse is ahead of Gradium on both datasets together, the Pipecat Dataset, 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
- Overall WER5.78%3.59%
- Pipecat Dataset WER6.48%3.66%
- Ocular Dataset WER4.45%3.46%
- Time to first text1.71s1.06s
- Final-text delay212ms201ms
Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide explains how word error rate is measured.
Gradium vs Pulse FAQ
Which is more accurate, Gradium or Smallest Pulse?
Smallest Pulse is more accurate on both datasets. On the 1,000 public Pipecat clips, Gradium scores 5.78% and Smallest Pulse 3.59%, so Smallest Pulse makes fewer errors by 2.19 points. On the eight licensed Ocular recordings, Gradium scores 6.48% and Smallest Pulse 3.66%, so Smallest Pulse makes fewer errors by 2.82 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Smallest Pulse is more accurate on both datasets. On the 1,000 public Pipecat clips, Gradium scores 5.78% and Smallest Pulse 3.59%, so Smallest Pulse makes fewer errors by 2.19 points. On the eight licensed Ocular recordings, Gradium scores 6.48% and Smallest Pulse 3.66%, so Smallest Pulse makes fewer errors by 2.82 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Smallest Pulse finishes the transcript 648ms sooner. Gradium has the final transcript 1.71s after the speaker stops and Smallest Pulse 1.06s, at the median. Both are measured on the same 206 streamed turns.
Smallest Pulse is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 648ms sooner. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Yes, both return partial text before the speaker stops. Gradium shows first text after 4.45% and Smallest Pulse after 3.46%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.