Left gets fewer words wrong. Lower has the final text ready sooner.
Soniox STT-RT v5 is ahead on time to first text and final-text delay, and Google Chirp 2 on both datasets together. The Pipecat Dataset and The Ocular Dataset are too close to call. Google Chirp 2 has a newer release: Google Chirp 3 vs Soniox STT-RT v5.
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 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Soniox STT-RT v5 3.02%, so Google Chirp 2 makes fewer errors by 0.01 points. On the 300 licensed Ocular turns, Google Chirp 2 scores 2.59% and Soniox STT-RT v5 2.54%, with likely ranges of 2.31 to 2.89% and 2.27 to 2.83%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Google Chirp 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Soniox STT-RT v5 3.02%, so Google Chirp 2 makes fewer errors by 0.01 points. On the 300 licensed Ocular turns, Google Chirp 2 scores 2.59% and Soniox STT-RT v5 2.54%, with likely ranges of 2.31 to 2.89% and 2.27 to 2.83%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Soniox STT-RT v5 finishes the transcript 3.30s sooner. Google Chirp 2 has the final transcript 4.50s after the speaker stops and Soniox STT-RT v5 1.20s, at the median. Both are measured on the same 206 streamed turns.
Soniox STT-RT v5 finishes the transcript 3.30s 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. Google Chirp 2 shows first text after 3.80% and Soniox STT-RT v5 after 3.92%, at the median.
Cekura runs these simulated calls on your agent and scores every one.