Inworld STT-1 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)
  • STT-12.72% · 41ms
  • Finch-Global3.17% · 51ms

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

Last updated Methodology by Dileep Chagam

Who is better at what

STT-1Finch-Global
  • Overall WER5.44%3.33%
  • Pipecat Dataset WER2.72%3.17%
  • Ocular Dataset WER10.60%3.62%
  • Time to first text1.06s1.83s
  • Final-text delay41ms51ms

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.

STT-1Finch-Global
  • ELO rating10311011–1043 · rank 1–13998981–1017 · rank 5–21
  • Expected win rate55%45%
  • Ocular turns WER · 172 draws of 19820 won6 won
  • Pipecat WER · 800 draws of 999147 won52 won
  • Semantic WER · 190 draws of 1987 won1 won
  • Phone line · 163 draws of 19724 won10 won
  • Call-center noise · 128 draws of 19834 won36 won
  • Babble noise · 112 draws of 19857 won29 won
  • TV noise · 138 draws of 19841 won19 won
  • Reverb · 131 draws of 19755 won11 won
  • Short replies · 60 draws of 708 won2 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

STT-1 vs Finch-Global FAQ

  • Murf Finch-Global is more accurate on the public clips. On the 1,000 public Pipecat clips, Inworld STT-1 scores 5.44% and Murf Finch-Global 3.33%, so Murf Finch-Global makes fewer errors by 2.11 points. On the 300 licensed Ocular turns, Inworld STT-1 scores 2.72% and Murf Finch-Global 3.17%, with likely ranges of 1.67 to 4.68% and 2.84 to 3.51%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. Inworld STT-1 finishes the transcript 770ms sooner. Inworld STT-1 has the final transcript 1.06s after the speaker stops and Murf Finch-Global 1.83s, at the median. Both are measured on the same 206 streamed turns.

  • Inworld STT-1 finishes the transcript 770ms sooner, and the two are too close to call on real conversations. 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. Inworld STT-1 shows first text after 10.60% 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.