Murf Finch-Global vs GPT-4o Mini Transcribe

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
  • 4o Mini Transcribe3.35% · 630ms

Murf Finch-Global is ahead of GPT-4o Mini Transcribe on both datasets together and final-text delay. The Pipecat Dataset and The Ocular Dataset are too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

Finch-Global4o Mini Transcribe
  • Overall WER3.33%3.73%
  • Pipecat Dataset WER3.17%3.35%
  • Ocular Dataset WER3.62%4.45%
  • Time to first text1.83sn/a
  • Final-text delay51ms630ms

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-Global4o Mini Transcribe
  • ELO rating998981–1017 · rank 5–211001993–1011 · rank 6–18
  • Expected win rate49%51%
  • Ocular turns WER · 159 draws of 19721 won17 won
  • Pipecat WER · 786 draws of 99968 won145 won
  • Semantic WER · 183 draws of 1976 won8 won
  • Phone line · 153 draws of 19825 won20 won
  • Call-center noise · 119 draws of 19849 won30 won
  • Babble noise · 101 draws of 19853 won44 won
  • TV noise · 100 draws of 19517 won78 won
  • Reverb · 118 draws of 19731 won48 won
  • Short replies · 57 draws of 708 won5 won
  • Entities · 40 draws of 492 won7 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 4o Mini Transcribe FAQ

  • Murf Finch-Global is more accurate on the public clips. On the 1,000 public Pipecat clips, Murf Finch-Global scores 3.33% and GPT-4o Mini Transcribe 3.73%, so Murf Finch-Global makes fewer errors by 0.41 points. On the 300 licensed Ocular turns, Murf Finch-Global scores 3.17% and GPT-4o Mini Transcribe 3.35%, with likely ranges of 2.84 to 3.51% and 3.08 to 3.65%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Final-text delay was not measured for one or both, so speed cannot be compared. Both are measured on the same 206 streamed turns.

  • Murf Finch-Global and GPT-4o Mini Transcribe are level on the two figures a voice agent depends on most. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.

  • Only Murf Finch-Global. GPT-4o Mini Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.

Test your voice agent the same way.

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