Cartesia Ink 2 vs Inworld STT-1
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Ink 22.39% · 123ms
- STT-12.72% · 41ms
Cartesia Ink 2 is ahead on both datasets together and the Ocular Dataset, and Inworld STT-1 on time to first text and final-text delay. The Pipecat Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER2.63%5.44%
- Pipecat Dataset WER2.39%2.72%
- Ocular Dataset WER3.09%10.60%
- Time to first text1.51s1.06s
- Final-text delay123ms41ms
Lower is better on every measure. Too close to call means the likely ranges overlap. For its voices, see our notes on Cartesia text to speech.
Ink 2 vs STT-1 FAQ
Which is more accurate, Cartesia Ink 2 or Inworld STT-1?
Cartesia Ink 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and Inworld STT-1 5.44%, so Cartesia Ink 2 makes fewer errors by 2.81 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 2.39% and Inworld STT-1 2.72%, with likely ranges of 2.13 to 2.65% 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.
Cartesia Ink 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and Inworld STT-1 5.44%, so Cartesia Ink 2 makes fewer errors by 2.81 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 2.39% and Inworld STT-1 2.72%, with likely ranges of 2.13 to 2.65% 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 448ms sooner. Cartesia Ink 2 has the final transcript 1.51s 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 448ms 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. Cartesia Ink 2 shows first text after 3.09% and Inworld STT-1 after 10.60%, at the median, so Cartesia Ink 2 is 7.52 points lower.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.