Google Chirp 2 vs Soniox STT-RT v5

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)
  • Chirp 22.59% · 568ms
  • STT-RT v52.54% · 38ms

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

Who is better at what

Chirp 2STT-RT v5
  • Overall WER3.01%3.02%
  • Pipecat Dataset WER2.59%2.54%
  • Ocular Dataset WER3.80%3.92%
  • Time to first text4.50s1.20s
  • Final-text delay568ms38ms

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.

Chirp 2STT-RT v5
  • ELO rating979966–999 · rank 9–211000986–1007 · rank 6–20
  • Expected win rate47%53%
  • Ocular turns WER · 152 draws of 19725 won20 won
  • Pipecat WER · 806 draws of 99990 won103 won
  • Semantic WER · 182 draws of 1977 won8 won
  • Phone line · 148 draws of 19826 won24 won
  • Call-center noise · 96 draws of 19844 won58 won
  • Babble noise · 83 draws of 19865 won50 won
  • TV noise · 90 draws of 19891 won17 won
  • Reverb · 130 draws of 19829 won39 won
  • Short replies · 49 draws of 7012 won9 won
  • Entities · 44 draws of 492 won3 won

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

Chirp 2 vs STT-RT v5 FAQ

  • 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.

Test your voice agent the same way.

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