Murf Finch-Global vs Reson8 Resonant-1

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)
  • Finch-Global3.17% · 51ms
  • Resonant-12.10% · 235ms

Murf Finch-Global is ahead on time to first text and final-text delay, and Reson8 Resonant-1 on both datasets together and the Pipecat Dataset. The Ocular Dataset is too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

Finch-GlobalResonant-1
  • Overall WER3.33%2.38%
  • Pipecat Dataset WER3.17%2.10%
  • Ocular Dataset WER3.62%2.93%
  • Time to first text1.83s2.40s
  • Final-text delay51ms235ms

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.

Finch-GlobalResonant-1
  • ELO rating998981–1017 · rank 5–2110341021–1047 · rank 1–10
  • Expected win rate45%55%
  • Ocular turns WER · 172 draws of 1986 won20 won
  • Pipecat WER · 849 draws of 99930 won120 won
  • Semantic WER · 190 draws of 1982 won6 won
  • Phone line · 172 draws of 1984 won22 won
  • Call-center noise · 130 draws of 19834 won34 won
  • Babble noise · 113 draws of 19839 won46 won
  • TV noise · 158 draws of 19712 won27 won
  • Reverb · 135 draws of 1975 won57 won
  • Short replies · 61 draws of 702 won7 won
  • Entities · 42 draws of 502 won6 won

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

Finch-Global vs Resonant-1 FAQ

  • Reson8 Resonant-1 is more accurate on both datasets. On the 1,000 public Pipecat clips, Murf Finch-Global scores 3.33% and Reson8 Resonant-1 2.38%, so Reson8 Resonant-1 makes fewer errors by 0.94 points. On the 300 licensed Ocular turns, Murf Finch-Global scores 3.17% and Reson8 Resonant-1 2.10%, so Reson8 Resonant-1 makes fewer errors by 1.07 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. Murf Finch-Global finishes the transcript 567ms sooner. Murf Finch-Global has the final transcript 1.83s after the speaker stops and Reson8 Resonant-1 2.40s, at the median. Both are measured on the same 206 streamed turns.

  • It is a trade-off. Reson8 Resonant-1 makes fewer errors on real conversations, while Murf Finch-Global finishes the transcript 567ms 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. Murf Finch-Global shows first text after 3.62% and Reson8 Resonant-1 after 2.93%, at the median.

Test your voice agent the same way.

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