ElevenLabs Scribe v3 Live vs NVIDIA Nemotron 3.5 Transcribe
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner. Nemotron 3.5 Transcribe doesn't support streaming, so it is not shown.
- Scribe v3 Live1.81% · 57ms
- Nemotron 3.5 Transcribe1.89%
ElevenLabs Scribe v3 Live is ahead of NVIDIA Nemotron 3.5 Transcribe 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%2.28%
- Pipecat Dataset WER1.81%1.89%
- Ocular Dataset WER2.05%3.03%
- Time to first text685msn/a
- Final-text delay57msn/a
Lower is better on every measure. Too close to call means the likely ranges overlap.
Scribe v3 Live vs Nemotron 3.5 Transcribe FAQ
Which is more accurate, ElevenLabs Scribe v3 Live or NVIDIA Nemotron 3.5 Transcribe?
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 NVIDIA Nemotron 3.5 Transcribe 2.28%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.39 points. On the 300 licensed Ocular turns, ElevenLabs Scribe v3 Live scores 1.81% and NVIDIA Nemotron 3.5 Transcribe 1.89%, with likely ranges of 1.59 to 2.04% and 1.63 to 2.17%. 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 NVIDIA Nemotron 3.5 Transcribe 2.28%, so ElevenLabs Scribe v3 Live makes fewer errors by 0.39 points. On the 300 licensed Ocular turns, ElevenLabs Scribe v3 Live scores 1.81% and NVIDIA Nemotron 3.5 Transcribe 1.89%, with likely ranges of 1.59 to 2.04% and 1.63 to 2.17%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
They cannot be compared on speed. NVIDIA Nemotron 3.5 Transcribe was tested on whole recordings rather than a live stream, so its speed is not measured.
The two are too close to call on real conversations. NVIDIA Nemotron 3.5 Transcribe was tested on whole recordings rather than a live stream, so its speed is not measured. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
NVIDIA Nemotron 3.5 Transcribe was tested on whole recordings rather than a live stream, so whether it streams partial text was not measured. ElevenLabs Scribe v3 Live returns partial text before the speaker stops.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.