Deepgram Flux English vs Gradium
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Flux English3.90% · 108ms
- Gradium6.48% · 212ms
Deepgram Flux English 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 WER4.00%5.78%
- Pipecat Dataset WER3.90%6.48%
- Ocular Dataset WER4.18%4.45%
- Time to first text791ms1.71s
- Final-text delay108ms212ms
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 Gradium FAQ
Which is more accurate, Deepgram Flux English or Gradium?
Deepgram Flux English is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux English scores 4.00% and Gradium 5.78%, so Deepgram Flux English makes fewer errors by 1.78 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 3.90% and Gradium 6.48%, so Deepgram Flux English makes fewer errors by 2.57 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Deepgram Flux English is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Flux English scores 4.00% and Gradium 5.78%, so Deepgram Flux English makes fewer errors by 1.78 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 3.90% and Gradium 6.48%, so Deepgram Flux English makes fewer errors by 2.57 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Deepgram Flux English finishes the transcript 914ms sooner. Deepgram Flux English has the final transcript 791ms after the speaker stops and Gradium 1.71s, at the median. Both are measured on the same 206 streamed turns.
Deepgram Flux English is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 914ms 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 English shows first text after 4.18% 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.