Deepgram Flux English vs Deepgram Nova-3
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Flux English3.90% · 108ms
- Nova-33.46% · 103ms
Deepgram Nova-3 is ahead on both datasets together and final-text delay, and Deepgram Flux English on time to first text. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER4.00%3.78%
- Pipecat Dataset WER3.90%3.46%
- Ocular Dataset WER4.18%4.39%
- Time to first text791ms1.06s
- Final-text delay108ms103ms
Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of Deepgram pricing.
Flux English vs Nova-3 FAQ
Which is more accurate, Deepgram Flux English or Deepgram Nova-3?
Deepgram Nova-3 is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Flux English scores 4.00% and Deepgram Nova-3 3.78%, so Deepgram Nova-3 makes fewer errors by 0.21 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 3.90% and Deepgram Nova-3 3.46%, with likely ranges of 3.53 to 4.29% and 3.16 to 3.78%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Deepgram Nova-3 is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Flux English scores 4.00% and Deepgram Nova-3 3.78%, so Deepgram Nova-3 makes fewer errors by 0.21 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 3.90% and Deepgram Nova-3 3.46%, with likely ranges of 3.53 to 4.29% and 3.16 to 3.78%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Deepgram Flux English finishes the transcript 273ms sooner. Deepgram Flux English has the final transcript 791ms after the speaker stops and Deepgram Nova-3 1.06s, at the median. Both are measured on the same 206 streamed turns.
Deepgram Flux English finishes the transcript 273ms sooner, and the two are too close to call on real conversations. 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 Flux English shows first text after 4.18% and Deepgram Nova-3 after 4.39%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.