Cartesia Ink 2 vs Fish Audio Transcribe Stream 1
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Ink 22.39% · 123ms
- Transcribe Stream 11.90% · 123ms
Fish Audio Transcribe Stream 1 is ahead of Cartesia Ink 2 on both datasets together and time to first text. The two tie on final-text delay. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER2.63%2.21%
- Pipecat Dataset WER2.39%1.90%
- Ocular Dataset WER3.09%2.78%
- Time to first text1.51s730ms
- Final-text delay123ms123ms
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 Transcribe Stream 1 FAQ
Which is more accurate, Cartesia Ink 2 or Fish Audio Transcribe Stream 1?
Fish Audio Transcribe Stream 1 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and Fish Audio Transcribe Stream 1 2.21%, so Fish Audio Transcribe Stream 1 makes fewer errors by 0.42 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 2.39% and Fish Audio Transcribe Stream 1 1.90%, with likely ranges of 2.13 to 2.65% and 1.68 to 2.14%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Fish Audio Transcribe Stream 1 is more accurate on the public clips. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and Fish Audio Transcribe Stream 1 2.21%, so Fish Audio Transcribe Stream 1 makes fewer errors by 0.42 points. On the eight licensed Ocular recordings, Cartesia Ink 2 scores 2.39% and Fish Audio Transcribe Stream 1 1.90%, with likely ranges of 2.13 to 2.65% and 1.68 to 2.14%. 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. Fish Audio Transcribe Stream 1 finishes the transcript 781ms sooner. Cartesia Ink 2 has the final transcript 1.51s after the speaker stops and Fish Audio Transcribe Stream 1 730ms, at the median. Both are measured on the same 206 streamed turns.
Fish Audio Transcribe Stream 1 finishes the transcript 781ms 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 Fish Audio Transcribe Stream 1 after 2.78%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.