Cartesia Ink 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)
  • Ink 22.39% · 123ms
  • STT-RT v52.54% · 38ms

Soniox STT-RT v5 is ahead on time to first text and final-text delay, and Cartesia Ink 2 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

Ink 2STT-RT v5
  • Overall WER2.63%3.02%
  • Pipecat Dataset WER2.39%2.54%
  • Ocular Dataset WER3.09%3.92%
  • Time to first text1.51s1.20s
  • Final-text delay123ms38ms

Lower is better on every measure. Too close to call means the likely ranges overlap. For its voices, see our notes on Cartesia text to speech.

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.

Ink 2STT-RT v5
  • ELO rating1014984–1031 · rank 2–201000986–1007 · rank 6–20
  • Expected win rate52%48%
  • Ocular turns WER · 160 draws of 19832 won6 won
  • Pipecat WER · 832 draws of 99994 won73 won
  • Semantic WER · 187 draws of 1989 won2 won
  • Phone line · 159 draws of 19832 won7 won
  • Call-center noise · 111 draws of 19828 won59 won
  • Babble noise · 105 draws of 19847 won46 won
  • TV noise · 142 draws of 19849 won7 won
  • Reverb · 146 draws of 19836 won16 won
  • Short replies · 53 draws of 7015 won2 won
  • Entities · 46 draws of 503 won1 won

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

Ink 2 vs STT-RT v5 FAQ

  • Cartesia Ink 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and Soniox STT-RT v5 3.02%, so Cartesia Ink 2 makes fewer errors by 0.39 points. On the 300 licensed Ocular turns, Cartesia Ink 2 scores 2.39% and Soniox STT-RT v5 2.54%, with likely ranges of 2.13 to 2.65% 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 316ms sooner. Cartesia Ink 2 has the final transcript 1.51s 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 316ms 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. Cartesia Ink 2 shows first text after 3.09% 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.