AssemblyAI Universal 3.6 Pro vs Murf Finch-Global

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
  • Finch-Global3.17% · 51ms

AssemblyAI Universal 3.6 Pro is ahead on both datasets together, the Pipecat Dataset and time to first text, and Murf Finch-Global on 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 ProFinch-Global
  • Overall WER2.71%3.33%
  • Pipecat Dataset WER1.77%3.17%
  • Ocular Dataset WER4.50%3.62%
  • Time to first text485ms1.83s
  • Final-text delay91ms51ms

Lower is better on every measure. Too close to call means the likely ranges overlap.

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 ProFinch-Global
  • ELO rating10211003–1031 · rank 2–16998981–1017 · rank 5–21
  • Expected win rate53%47%
  • Ocular turns WER · 163 draws of 19617 won16 won
  • Pipecat WER · 806 draws of 999148 won45 won
  • Semantic WER · 190 draws of 1965 won1 won
  • Phone line · 161 draws of 19823 won14 won
  • Call-center noise · 136 draws of 19836 won26 won
  • Babble noise · 111 draws of 19852 won35 won
  • TV noise · 150 draws of 19822 won26 won
  • Reverb · 129 draws of 19756 won12 won
  • Short replies · 61 draws of 684 won3 won
  • Entities · 41 draws of 507 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 Finch-Global 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 Murf Finch-Global 3.33%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 0.62 points. On the 300 licensed Ocular turns, AssemblyAI Universal 3.6 Pro scores 1.77% and Murf Finch-Global 3.17%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 1.40 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. AssemblyAI Universal 3.6 Pro finishes the transcript 1.35s sooner. AssemblyAI Universal 3.6 Pro has the final transcript 485ms after the speaker stops and Murf Finch-Global 1.83s, 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 1.35s 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 Murf Finch-Global after 3.62%, at the median.

Test your voice agent the same way.

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