Google Chirp 3 vs Inworld STT-1
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Chirp 32.00% · 475ms
- STT-12.72% · 41ms
Inworld STT-1 is ahead on time to first text and final-text delay, and Google Chirp 3 on both datasets together. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER2.76%5.44%
- Pipecat Dataset WER2.00%2.72%
- Ocular Dataset WER4.19%10.60%
- Time to first text4.48s1.06s
- Final-text delay475ms41ms
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 3 vs STT-1 FAQ
Which is more accurate, Google Chirp 3 or Inworld STT-1?
Google Chirp 3 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 3 scores 2.76% and Inworld STT-1 5.44%, so Google Chirp 3 makes fewer errors by 2.68 points. On the eight licensed Ocular recordings, Google Chirp 3 scores 2.00% and Inworld STT-1 2.72%, with likely ranges of 1.77 to 2.25% 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 3 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 3 scores 2.76% and Inworld STT-1 5.44%, so Google Chirp 3 makes fewer errors by 2.68 points. On the eight licensed Ocular recordings, Google Chirp 3 scores 2.00% and Inworld STT-1 2.72%, with likely ranges of 1.77 to 2.25% 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 3.42s sooner. Google Chirp 3 has the final transcript 4.48s 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 3.42s 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 3 shows first text after 4.19% 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.