AssemblyAI Universal 3.6 Pro vs Google Chirp 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)
  • Universal 3.6 Pro1.77% · 91ms
  • Chirp 22.59% · 568ms

AssemblyAI Universal 3.6 Pro is ahead of Google Chirp 2 on both datasets together, the Pipecat Dataset, time to first text and final-text delay. The Ocular Dataset is too close to call. Google Chirp 2 has a newer release: AssemblyAI Universal 3.6 Pro vs Google Chirp 3.

Last updated Methodology by Dileep Chagam

Who is better at what

Universal 3.6 ProChirp 2
  • Overall WER2.71%3.01%
  • Pipecat Dataset WER1.77%2.59%
  • Ocular Dataset WER4.50%3.80%
  • Time to first text485ms4.50s
  • Final-text delay91ms568ms

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.

Universal 3.6 ProChirp 2
  • ELO rating10211003–1031 · rank 2–16979966–999 · rank 9–21
  • Expected win rate56%44%
  • Ocular turns WER · 156 draws of 19523 won16 won
  • Pipecat WER · 829 draws of 999123 won47 won
  • Semantic WER · 179 draws of 19510 won6 won
  • Phone line · 156 draws of 19828 won14 won
  • Call-center noise · 115 draws of 19860 won23 won
  • Babble noise · 100 draws of 19861 won37 won
  • TV noise · 119 draws of 19826 won53 won
  • Reverb · 140 draws of 19842 won16 won
  • Short replies · 57 draws of 688 won3 won
  • Entities · 45 draws of 494 won0 won

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

Universal 3.6 Pro vs Chirp 2 FAQ

  • AssemblyAI Universal 3.6 Pro is more accurate on both datasets. On the 1,000 public Pipecat clips, AssemblyAI Universal 3.6 Pro scores 2.71% and Google Chirp 2 3.01%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 0.30 points. On the 300 licensed Ocular turns, AssemblyAI Universal 3.6 Pro scores 1.77% and Google Chirp 2 2.59%, so AssemblyAI Universal 3.6 Pro makes fewer errors by 0.82 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. AssemblyAI Universal 3.6 Pro finishes the transcript 4.01s sooner. AssemblyAI Universal 3.6 Pro has the final transcript 485ms after the speaker stops and Google Chirp 2 4.50s, at the median. Both are measured on the same 206 streamed turns.

  • AssemblyAI Universal 3.6 Pro is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 4.01s 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 Universal 3.6 Pro shows first text after 4.50% and Google Chirp 2 after 3.80%, at the median.

Test your voice agent the same way.

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