Deepgram Nova-3vsInworld STT-1
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Nova-33.46% · 103ms
- STT-12.72% · 41ms
Inworld STT-1 is ahead of Deepgram Nova-3 on final-text delay. The two tie on time to first text. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Pipecat Dataset WER3.46%2.72%
- Ocular Dataset WER4.39%10.60%
- Time to first text1.06s1.06s
- Final-text delay103ms41ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Nova-3 vs STT-1 FAQ
Which is more accurate, Deepgram Nova-3 or Inworld STT-1?
Deepgram Nova-3 and Inworld STT-1 are too close to call on accuracy. On the 1,000 public Pipecat clips, Deepgram Nova-3 scores 3.46% and Inworld STT-1 2.72%, with likely ranges of 3.16 to 3.78% and 1.67 to 4.68%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Deepgram Nova-3 scores 4.39% and Inworld STT-1 10.60%, with likely ranges of 3.42 to 5.25% and 3.85 to 22.76%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Deepgram Nova-3 and Inworld STT-1 are too close to call on accuracy. On the 1,000 public Pipecat clips, Deepgram Nova-3 scores 3.46% and Inworld STT-1 2.72%, with likely ranges of 3.16 to 3.78% and 1.67 to 4.68%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Deepgram Nova-3 scores 4.39% and Inworld STT-1 10.60%, with likely ranges of 3.42 to 5.25% and 3.85 to 22.76%. 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. Inworld STT-1 finishes the transcript 62ms sooner. Deepgram Nova-3 has the final transcript 103ms after the speaker stops and Inworld STT-1 41ms, at the median. Both are measured on the same 206 streamed turns.
Inworld STT-1 finishes the transcript 62ms 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. Deepgram Nova-3 shows first text after 1.06s and Inworld STT-1 after 1.06s, at the median.