Deepgram Flux MultilingualvsDeepgram Nova-3
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Flux Multilingual4.96% · 114ms
- Nova-33.46% · 103ms
Deepgram Nova-3 is ahead on the Pipecat Dataset and final-text delay, and Deepgram Flux Multilingual on time to first text. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Pipecat Dataset WER4.96%3.46%
- Ocular Dataset WER4.53%4.39%
- Time to first text793ms1.06s
- Final-text delay114ms103ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Flux Multilingual vs Nova-3 FAQ
Which is more accurate, Deepgram Flux Multilingual or Deepgram Nova-3?
Deepgram Nova-3 is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Flux Multilingual scores 4.96% and Deepgram Nova-3 3.46%, so Deepgram Nova-3 makes fewer errors by 1.50 points. On the eight licensed Ocular recordings, Deepgram Flux Multilingual scores 4.53% and Deepgram Nova-3 4.39%, with likely ranges of 3.29 to 5.69% and 3.42 to 5.25%. 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 Multilingual scores 4.96% and Deepgram Nova-3 3.46%, so Deepgram Nova-3 makes fewer errors by 1.50 points. On the eight licensed Ocular recordings, Deepgram Flux Multilingual scores 4.53% and Deepgram Nova-3 4.39%, with likely ranges of 3.29 to 5.69% and 3.42 to 5.25%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Deepgram Nova-3 finishes the transcript 11ms sooner. Deepgram Flux Multilingual has the final transcript 114ms after the speaker stops and Deepgram Nova-3 103ms, at the median. Both are measured on the same 206 streamed turns.
Deepgram Nova-3 finishes the transcript 11ms 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 Multilingual shows first text after 793ms and Deepgram Nova-3 after 1.06s, at the median, so Deepgram Flux Multilingual is 271ms sooner.