Deepgram Flux Multilingual vs Gradium
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Flux Multilingual4.96% · 114ms
- Gradium6.48% · 212ms
Deepgram Flux Multilingual 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 WER4.81%5.78%
- Pipecat Dataset WER4.96%6.48%
- Ocular Dataset WER4.53%4.45%
- Time to first text793ms1.71s
- Final-text delay114ms212ms
Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of Deepgram pricing.
Flux Multilingual vs Gradium FAQ
Which is more accurate, Deepgram Flux Multilingual or Gradium?
Deepgram Flux Multilingual is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux Multilingual scores 4.81% and Gradium 5.78%, so Deepgram Flux Multilingual makes fewer errors by 0.97 points. On the eight licensed Ocular recordings, Deepgram Flux Multilingual scores 4.96% and Gradium 6.48%, so Deepgram Flux Multilingual makes fewer errors by 1.52 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Deepgram Flux Multilingual is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux Multilingual scores 4.81% and Gradium 5.78%, so Deepgram Flux Multilingual makes fewer errors by 0.97 points. On the eight licensed Ocular recordings, Deepgram Flux Multilingual scores 4.96% and Gradium 6.48%, so Deepgram Flux Multilingual makes fewer errors by 1.52 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Deepgram Flux Multilingual finishes the transcript 912ms sooner. Deepgram Flux Multilingual has the final transcript 793ms after the speaker stops and Gradium 1.71s, at the median. Both are measured on the same 206 streamed turns.
Deepgram Flux Multilingual is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 912ms 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 Flux Multilingual shows first text after 4.53% and Gradium after 4.45%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.