Deepgram Nova-3 vs GPT Realtime Whisper
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Nova-33.46% · 103ms
- Realtime Whisper2.16% · 543ms
Deepgram Nova-3 is ahead on time to first text and final-text delay, and GPT Realtime Whisper 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
- Overall WER3.78%2.63%
- Pipecat Dataset WER3.46%2.16%
- Ocular Dataset WER4.39%3.53%
- Time to first text1.06s1.38s
- Final-text delay103ms543ms
Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of Deepgram pricing.
Nova-3 vs Realtime Whisper FAQ
Which is more accurate, Deepgram Nova-3 or GPT Realtime Whisper?
GPT Realtime Whisper is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Nova-3 scores 3.78% and GPT Realtime Whisper 2.63%, so GPT Realtime Whisper makes fewer errors by 1.16 points. On the eight licensed Ocular recordings, Deepgram Nova-3 scores 3.46% and GPT Realtime Whisper 2.16%, so GPT Realtime Whisper makes fewer errors by 1.31 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, Deepgram Nova-3 scores 3.78% and GPT Realtime Whisper 2.63%, so GPT Realtime Whisper makes fewer errors by 1.16 points. On the eight licensed Ocular recordings, Deepgram Nova-3 scores 3.46% and GPT Realtime Whisper 2.16%, so GPT Realtime Whisper makes fewer errors by 1.31 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Deepgram Nova-3 finishes the transcript 315ms sooner. Deepgram Nova-3 has the final transcript 1.06s after the speaker stops and GPT Realtime Whisper 1.38s, 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 Deepgram Nova-3 finishes the transcript 315ms 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. Deepgram Nova-3 shows first text after 4.39% and GPT Realtime Whisper after 3.53%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.