Google Chirp 2 vs Inworld STT-1
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Chirp 22.59% · 568ms
- STT-12.72% · 41ms
Inworld STT-1 is ahead on time to first text and final-text delay, and Google Chirp 2 on both datasets together. The Pipecat Dataset and The Ocular Dataset are too close to call. Google Chirp 2 has a newer release: Google Chirp 3 vs Inworld STT-1.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.01%5.44%
- Pipecat Dataset WER2.59%2.72%
- Ocular Dataset WER3.80%10.60%
- Time to first text4.50s1.06s
- Final-text delay568ms41ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Chirp 2 vs STT-1 FAQ
Which is more accurate, Google Chirp 2 or Inworld STT-1?
Google Chirp 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Inworld STT-1 5.44%, so Google Chirp 2 makes fewer errors by 2.43 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and Inworld STT-1 2.72%, with likely ranges of 2.31 to 2.89% and 1.67 to 4.68%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Google Chirp 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 2 scores 3.01% and Inworld STT-1 5.44%, so Google Chirp 2 makes fewer errors by 2.43 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 2.59% and Inworld STT-1 2.72%, with likely ranges of 2.31 to 2.89% and 1.67 to 4.68%. 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. Inworld STT-1 finishes the transcript 3.43s sooner. Google Chirp 2 has the final transcript 4.50s after the speaker stops and Inworld STT-1 1.06s, at the median. Both are measured on the same 206 streamed turns.
Inworld STT-1 finishes the transcript 3.43s 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. Google Chirp 2 shows first text after 3.80% and Inworld STT-1 after 10.60%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.