Google Chirp 2 vs Gradium
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Chirp 22.59% · 568ms
- Gradium6.48% · 212ms
Google Chirp 2 is ahead on both datasets together and the Pipecat Dataset, and Gradium on time to first text and final-text delay. The Ocular Dataset is too close to call. Google Chirp 2 has a newer release: Google Chirp 3 vs Gradium.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.01%5.78%
- Pipecat Dataset WER2.59%6.48%
- Ocular Dataset WER3.80%4.45%
- Time to first text4.50s1.71s
- Final-text delay568ms212ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Chirp 2 vs Gradium FAQ
Which is more accurate, Google Chirp 2 or Gradium?
Google Chirp 2 is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Gradium 5.78%, so Google Chirp 2 makes fewer errors by 2.77 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and Gradium 6.48%, so Google Chirp 2 makes fewer errors by 3.89 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Google Chirp 2 is more accurate on both datasets. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Gradium 5.78%, so Google Chirp 2 makes fewer errors by 2.77 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and Gradium 6.48%, so Google Chirp 2 makes fewer errors by 3.89 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. Gradium finishes the transcript 2.79s sooner. Google Chirp 2 has the final transcript 4.50s after the speaker stops and Gradium 1.71s, at the median. Both are measured on the same 206 streamed turns.
It is a trade-off. Google Chirp 2 makes fewer errors on real conversations, while Gradium finishes the transcript 2.79s 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 Gradium after 4.45%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.