AssemblyAI STT 3.7 Realtime Agent vs Cartesia Ink 2

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 3.7 Realtime Agent1.68% · 47ms
  • Ink 22.39% · 123ms

AssemblyAI STT 3.7 Realtime Agent is ahead of Cartesia Ink 2 on both datasets together, the Pipecat Dataset, time to first text and final-text delay. The Ocular Dataset is too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

STT 3.7 Realtime AgentInk 2
  • Overall WER2.41%2.63%
  • Pipecat Dataset WER1.68%2.39%
  • Ocular Dataset WER3.81%3.09%
  • Time to first text493ms1.51s
  • Final-text delay47ms123ms

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 3.7 Realtime AgentInk 2
  • ELO rating10241001–1039 · rank 1–161014984–1031 · rank 2–20
  • Expected win rate51%49%
  • Ocular turns WER · 179 draws of 1988 won11 won
  • Pipecat WER · 891 draws of 99972 won36 won
  • Semantic WER · 190 draws of 1982 won6 won
  • Phone line · 178 draws of 1989 won11 won
  • Call-center noise · 110 draws of 19770 won17 won
  • Babble noise · 119 draws of 19759 won19 won
  • TV noise · 150 draws of 19835 won13 won
  • Reverb · 170 draws of 19814 won14 won
  • Short replies · 65 draws of 702 won3 won
  • Entities · 47 draws of 502 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

STT 3.7 Realtime Agent vs Ink 2 FAQ

  • AssemblyAI STT 3.7 Realtime Agent is more accurate on both datasets. On the 1,000 public Pipecat clips, AssemblyAI STT 3.7 Realtime Agent scores 2.41% and Cartesia Ink 2 2.63%, so AssemblyAI STT 3.7 Realtime Agent makes fewer errors by 0.21 points. On the 300 licensed Ocular turns, AssemblyAI STT 3.7 Realtime Agent scores 1.68% and Cartesia Ink 2 2.39%, so AssemblyAI STT 3.7 Realtime Agent makes fewer errors by 0.71 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. AssemblyAI STT 3.7 Realtime Agent finishes the transcript 1.02s sooner. AssemblyAI STT 3.7 Realtime Agent has the final transcript 493ms after the speaker stops and Cartesia Ink 2 1.51s, at the median. Both are measured on the same 206 streamed turns.

  • AssemblyAI STT 3.7 Realtime Agent is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 1.02s 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. AssemblyAI STT 3.7 Realtime Agent shows first text after 3.81% and Cartesia Ink 2 after 3.09%, at the median.

Test your voice agent the same way.

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