Left gets fewer words wrong. Lower has the final text ready sooner.
Google Chirp 3 is ahead on both datasets together and the Pipecat Dataset, and Murf Finch-Global on time to first text and final-text delay. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Lower is better on every measure. Too close to call means the likely ranges overlap.
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.
Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out
Google Chirp 3 is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 3 scores 2.76% and Murf Finch-Global 3.33%, so Google Chirp 3 makes fewer errors by 0.57 points. On the 300 licensed Ocular turns, Google Chirp 3 scores 2.00% and Murf Finch-Global 3.17%, so Google Chirp 3 makes fewer errors by 1.17 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Google Chirp 3 is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 3 scores 2.76% and Murf Finch-Global 3.33%, so Google Chirp 3 makes fewer errors by 0.57 points. On the 300 licensed Ocular turns, Google Chirp 3 scores 2.00% and Murf Finch-Global 3.17%, so Google Chirp 3 makes fewer errors by 1.17 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Murf Finch-Global finishes the transcript 2.65s sooner. Google Chirp 3 has the final transcript 4.48s after the speaker stops and Murf Finch-Global 1.83s, at the median. Both are measured on the same 206 streamed turns.
It is a trade-off. Google Chirp 3 makes fewer errors on real conversations, while Murf Finch-Global finishes the transcript 2.65s 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. Google Chirp 3 shows first text after 4.19% and Murf Finch-Global after 3.62%, at the median.
Cekura runs these simulated calls on your agent and scores every one.