Cartesia Ink 2 vs ElevenLabs Scribe v3 Live
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Ink 22.39% · 123ms
- Scribe v3 Live1.81% · 57ms
ElevenLabs Scribe v3 Live is ahead of Cartesia Ink 2 on both datasets together, the Pipecat Dataset, time to first text and final-text delay. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER2.63%1.89%
- Pipecat Dataset WER2.39%1.81%
- Ocular Dataset WER3.09%2.05%
- Time to first text1.51s685ms
- Final-text delay123ms57ms
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 Scribe v3 Live FAQ
Which is more accurate, Cartesia Ink 2 or ElevenLabs Scribe v3 Live?
ElevenLabs Scribe v3 Live is more accurate on both datasets. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and ElevenLabs Scribe v3 Live 1.89%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.74 points. On the 300 licensed Ocular turns, Cartesia Ink 2 scores 2.39% and ElevenLabs Scribe v3 Live 1.81%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.57 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
ElevenLabs Scribe v3 Live is more accurate on both datasets. On the 1,000 public Pipecat clips, Cartesia Ink 2 scores 2.63% and ElevenLabs Scribe v3 Live 1.89%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.74 points. On the 300 licensed Ocular turns, Cartesia Ink 2 scores 2.39% and ElevenLabs Scribe v3 Live 1.81%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.57 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. ElevenLabs Scribe v3 Live finishes the transcript 826ms sooner. Cartesia Ink 2 has the final transcript 1.51s after the speaker stops and ElevenLabs Scribe v3 Live 685ms, at the median. Both are measured on the same 206 streamed turns.
ElevenLabs Scribe v3 Live is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 826ms 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. Cartesia Ink 2 shows first text after 3.09% and ElevenLabs Scribe v3 Live after 2.05%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.