AssemblyAI Universal 3.6 Pro vs Deepgram Flux Multilingual

Compare

Accuracy and speed

Left gets fewer words wrong. Lower has the final text ready sooner.

Accurate and fast0ms200ms400ms600ms800ms0%2%4%6%Words wrong on clean audio (Pipecat WER)
  • Universal 3.6 Pro1.77% · 91ms
  • Flux Multilingual4.96% · 114ms

AssemblyAI Universal 3.6 Pro is ahead of Deepgram Flux Multilingual 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

Universal 3.6 ProFlux Multilingual
  • Overall WER2.71%4.81%
  • Pipecat Dataset WER1.77%4.96%
  • Ocular Dataset WER4.50%4.53%
  • Time to first text485ms793ms
  • Final-text delay91ms114ms

Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of AssemblyAI pricing.

Clip by clip

On every clip both models were scored on, the lower WER wins, and WERs within 5 points of each other are a draw; in the rating, a wider win counts for more. Expected win rate is what the two ELO ratings predict for a match.

Universal 3.6 ProFlux Multilingual
  • ELO rating10211003–1031 · rank 2–16936916–966 · rank 18–23
  • Expected win rate62%38%
  • Ocular turns WER · 144 draws of 19433 won17 won
  • Pipecat WER · 735 draws of 999232 won32 won
  • Semantic WER · 182 draws of 19410 won2 won
  • Phone line · 149 draws of 19836 won13 won
  • Call-center noise · 97 draws of 19584 won14 won
  • Babble noise · 66 draws of 185101 won18 won
  • TV noise · 121 draws of 19561 won13 won
  • Reverb · 121 draws of 19862 won15 won
  • Short replies · 48 draws of 6714 won5 won
  • Entities · 41 draws of 496 won2 won

Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out

Universal 3.6 Pro vs Flux Multilingual FAQ

  • AssemblyAI Universal 3.6 Pro is more accurate on both datasets. On the 1,000 public Pipecat clips, AssemblyAI Universal 3.6 Pro scores 2.71% and Deepgram Flux Multilingual 4.81%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 2.10 points. On the 300 licensed Ocular turns, AssemblyAI Universal 3.6 Pro scores 1.77% and Deepgram Flux Multilingual 4.96%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 3.19 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. AssemblyAI Universal 3.6 Pro finishes the transcript 308ms sooner. AssemblyAI Universal 3.6 Pro has the final transcript 485ms after the speaker stops and Deepgram Flux Multilingual 793ms, at the median. Both are measured on the same 206 streamed turns.

  • AssemblyAI Universal 3.6 Pro is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 308ms 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. AssemblyAI Universal 3.6 Pro shows first text after 4.50% and Deepgram Flux Multilingual after 4.53%, at the median.

Test your voice agent the same way.

Cekura runs these simulated calls on your agent and scores every one.