Deepgram Nova-3 vs ElevenLabs Scribe v3 Live
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Nova-33.46% · 103ms
- Scribe v3 Live1.81% · 57ms
ElevenLabs Scribe v3 Live is ahead of Deepgram Nova-3 on all five metrics.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.78%1.89%
- Pipecat Dataset WER3.46%1.81%
- Ocular Dataset WER4.39%2.05%
- Time to first text1.06s685ms
- Final-text delay103ms57ms
Lower is better on every measure. Too close to call means the likely ranges overlap. For costs, see our breakdown of Deepgram pricing.
Nova-3 vs Scribe v3 Live FAQ
Which is more accurate, Deepgram Nova-3 or ElevenLabs Scribe v3 Live?
ElevenLabs Scribe v3 Live is more accurate on both datasets. On the 1,000 public Pipecat clips, Deepgram Nova-3 scores 3.78% and ElevenLabs Scribe v3 Live 1.89%, so ElevenLabs Scribe v3 Live makes fewer errors by 1.89 points. On the 300 licensed Ocular turns, Deepgram Nova-3 scores 3.46% and ElevenLabs Scribe v3 Live 1.81%, so ElevenLabs Scribe v3 Live makes fewer errors by 1.65 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, Deepgram Nova-3 scores 3.78% and ElevenLabs Scribe v3 Live 1.89%, so ElevenLabs Scribe v3 Live makes fewer errors by 1.89 points. On the 300 licensed Ocular turns, Deepgram Nova-3 scores 3.46% and ElevenLabs Scribe v3 Live 1.81%, so ElevenLabs Scribe v3 Live makes fewer errors by 1.65 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
No. ElevenLabs Scribe v3 Live finishes the transcript 379ms sooner. Deepgram Nova-3 has the final transcript 1.06s 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 379ms 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. Deepgram Nova-3 shows first text after 4.39% and ElevenLabs Scribe v3 Live after 2.05%, at the median, so ElevenLabs Scribe v3 Live is 2.35 points lower.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.