Google Chirp 2 vs Google Chirp 3
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Chirp 22.59% · 568ms
- Chirp 32.00% · 475ms
Google Chirp 3 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.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.01%2.76%
- Pipecat Dataset WER2.59%2.00%
- Ocular Dataset WER3.80%4.19%
- Time to first text4.50s4.48s
- Final-text delay568ms475ms
Lower is better on every measure. Too close to call means the likely ranges overlap. For the wider field, see our pick of the best voice AI APIs for real-time audio.
Chirp 2 vs Chirp 3 FAQ
Which is more accurate, Google Chirp 2 or Google Chirp 3?
Google Chirp 3 is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Google Chirp 3 2.76%, so Google Chirp 3 makes fewer errors by 0.25 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and Google Chirp 3 2.00%, so Google Chirp 3 makes fewer errors by 0.59 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Google Chirp 3 is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Google Chirp 3 2.76%, so Google Chirp 3 makes fewer errors by 0.25 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and Google Chirp 3 2.00%, so Google Chirp 3 makes fewer errors by 0.59 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Google Chirp 3 finishes the transcript 17ms sooner. Google Chirp 2 has the final transcript 4.50s after the speaker stops and Google Chirp 3 4.48s, at the median. Both are measured on the same 206 streamed turns.
Google Chirp 3 is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 17ms 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. Google Chirp 2 shows first text after 3.80% and Google Chirp 3 after 4.19%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.