ElevenLabs Scribe v3 Live vs Reson8 Rumble-2
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Scribe v3 Live1.81% · 57ms
- Rumble-21.69% · 18ms
Reson8 Rumble-2 is ahead on time to first text and final-text delay, and ElevenLabs Scribe v3 Live 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 WER1.89%2.05%
- Pipecat Dataset WER1.81%1.69%
- Ocular Dataset WER2.05%2.75%
- Time to first text685ms486ms
- Final-text delay57ms18ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Scribe v3 Live vs Rumble-2 FAQ
Which is more accurate, ElevenLabs Scribe v3 Live or Reson8 Rumble-2?
ElevenLabs Scribe v3 Live is more accurate on the public clips. On the 1,000 public Pipecat clips, ElevenLabs Scribe v3 Live scores 1.89% and Reson8 Rumble-2 2.05%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.16 points. On the 300 licensed Ocular turns, ElevenLabs Scribe v3 Live scores 1.81% and Reson8 Rumble-2 1.69%, with likely ranges of 1.59 to 2.04% and 1.48 to 1.92%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
ElevenLabs Scribe v3 Live is more accurate on the public clips. On the 1,000 public Pipecat clips, ElevenLabs Scribe v3 Live scores 1.89% and Reson8 Rumble-2 2.05%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.16 points. On the 300 licensed Ocular turns, ElevenLabs Scribe v3 Live scores 1.81% and Reson8 Rumble-2 1.69%, with likely ranges of 1.59 to 2.04% and 1.48 to 1.92%. 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. Reson8 Rumble-2 finishes the transcript 199ms sooner. ElevenLabs Scribe v3 Live has the final transcript 685ms after the speaker stops and Reson8 Rumble-2 486ms, at the median. Both are measured on the same 206 streamed turns.
Reson8 Rumble-2 finishes the transcript 199ms 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. ElevenLabs Scribe v3 Live shows first text after 2.05% and Reson8 Rumble-2 after 2.75%, at the median.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.