GPT Realtime Whisper vs Smallest Pulse
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Realtime Whisper2.16% · 543ms
- Pulse3.66% · 201ms
GPT Realtime Whisper is ahead on both datasets together and the Pipecat Dataset, and Smallest Pulse 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
- Overall WER2.63%3.59%
- Pipecat Dataset WER2.16%3.66%
- Ocular Dataset WER3.53%3.46%
- Time to first text1.38s1.06s
- Final-text delay543ms201ms
Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide covers testing OpenAI Realtime API voice agents.
Realtime Whisper vs Pulse FAQ
Which is more accurate, GPT Realtime Whisper or Smallest Pulse?
GPT Realtime Whisper is more accurate on both datasets. On the 1,000 public Pipecat clips, GPT Realtime Whisper scores 2.63% and Smallest Pulse 3.59%, so GPT Realtime Whisper makes fewer errors by 0.96 points. On the eight licensed Ocular recordings, GPT Realtime Whisper scores 2.16% and Smallest Pulse 3.66%, so GPT Realtime Whisper makes fewer errors by 1.50 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
GPT Realtime Whisper is more accurate on both datasets. On the 1,000 public Pipecat clips, GPT Realtime Whisper scores 2.63% and Smallest Pulse 3.59%, so GPT Realtime Whisper makes fewer errors by 0.96 points. On the eight licensed Ocular recordings, GPT Realtime Whisper scores 2.16% and Smallest Pulse 3.66%, so GPT Realtime Whisper makes fewer errors by 1.50 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Smallest Pulse finishes the transcript 322ms sooner. GPT Realtime Whisper has the final transcript 1.38s after the speaker stops and Smallest Pulse 1.06s, at the median. Both are measured on the same 206 streamed turns.
It is a trade-off. GPT Realtime Whisper makes fewer errors on real conversations, while Smallest Pulse finishes the transcript 322ms 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. GPT Realtime Whisper shows first text after 3.53% 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.