Deepgram Flux EnglishvsSpeechmatics Linden
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- Flux English3.90% · 108ms
- Linden2.46% · 147ms
Deepgram Flux English is ahead on time to first text and final-text delay, and Speechmatics Linden on the Pipecat Dataset. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Pipecat Dataset WER3.90%2.46%
- Ocular Dataset WER4.18%3.93%
- Time to first text791ms1.19s
- Final-text delay108ms147ms
Lower is better on every measure. Too close to call means the likely ranges overlap.
Flux English vs Linden FAQ
Which is more accurate, Deepgram Flux English or Speechmatics Linden?
Speechmatics Linden is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Flux English scores 3.90% and Speechmatics Linden 2.46%, so Speechmatics Linden makes fewer errors by 1.45 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 4.18% and Speechmatics Linden 3.93%, with likely ranges of 3.08 to 5.23% and 2.94 to 5.19%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Speechmatics Linden is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Flux English scores 3.90% and Speechmatics Linden 2.46%, so Speechmatics Linden makes fewer errors by 1.45 points. On the eight licensed Ocular recordings, Deepgram Flux English scores 4.18% and Speechmatics Linden 3.93%, with likely ranges of 3.08 to 5.23% and 2.94 to 5.19%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Yes. Deepgram Flux English finishes the transcript 39ms sooner. Deepgram Flux English has the final transcript 108ms after the speaker stops and Speechmatics Linden 147ms, at the median. Both are measured on the same 206 streamed turns.
Deepgram Flux English finishes the transcript 39ms 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 Flux English shows first text after 791ms and Speechmatics Linden after 1.19s, at the median, so Deepgram Flux English is 399ms sooner.