AssemblyAI STT 3.7 Realtime Agent vs Speechmatics Linden

Compare

Accuracy and speed

Left gets fewer words wrong. Lower has the final text ready sooner.

Accurate and fast0ms200ms400ms600ms800ms0%2%4%6%Words wrong on clean audio (Pipecat WER)
  • STT 3.7 Realtime Agent1.68% · 47ms
  • Linden2.46% · 147ms

AssemblyAI STT 3.7 Realtime Agent is ahead of Speechmatics Linden on both datasets together, the Pipecat Dataset, time to first text and final-text delay. The Ocular Dataset is too close to call.

Last updated Methodology by Dileep Chagam

Who is better at what

STT 3.7 Realtime AgentLinden
  • Overall WER2.41%2.97%
  • Pipecat Dataset WER1.68%2.46%
  • Ocular Dataset WER3.81%3.93%
  • Time to first text493ms1.19s
  • Final-text delay47ms147ms

Lower is better on every measure. Too close to call means the likely ranges overlap.

Clip by clip

On every clip both models were scored on, the lower WER wins, and WERs within 5 points of each other are a draw; in the rating, a wider win counts for more. Expected win rate is what the two ELO ratings predict for a match.

STT 3.7 Realtime AgentLinden
  • ELO rating10241001–1039 · rank 1–16981959–989 · rank 13–22
  • Expected win rate56%44%
  • Ocular turns WER · 169 draws of 19720 won8 won
  • Pipecat WER · 836 draws of 998120 won42 won
  • Semantic WER · 189 draws of 1976 won2 won
  • Phone line · 161 draws of 18716 won10 won
  • Call-center noise · 94 draws of 18985 won10 won
  • Babble noise · 97 draws of 18478 won9 won
  • TV noise · 112 draws of 19176 won3 won
  • Reverb · 154 draws of 18719 won14 won
  • Short replies · 66 draws of 702 won2 won
  • Entities · 48 draws of 502 won0 won

Short replies are decided on the error count and entities on exact capture, with no draw margin. How the rating is worked out

STT 3.7 Realtime Agent vs Linden FAQ

  • AssemblyAI STT 3.7 Realtime Agent is more accurate on both datasets. On the 1,000 public Pipecat clips, AssemblyAI STT 3.7 Realtime Agent scores 2.41% and Speechmatics Linden 2.97%, so AssemblyAI STT 3.7 Realtime Agent makes fewer errors by 0.55 points. On the 300 licensed Ocular turns, AssemblyAI STT 3.7 Realtime Agent scores 1.68% and Speechmatics Linden 2.46%, so AssemblyAI STT 3.7 Realtime Agent makes fewer errors by 0.78 points. Word error rate counts incorrect, missing, and extra words, so lower is better.

  • Yes. AssemblyAI STT 3.7 Realtime Agent finishes the transcript 697ms sooner. AssemblyAI STT 3.7 Realtime Agent has the final transcript 493ms after the speaker stops and Speechmatics Linden 1.19s, at the median. Both are measured on the same 206 streamed turns.

  • AssemblyAI STT 3.7 Realtime Agent is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 697ms 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. AssemblyAI STT 3.7 Realtime Agent shows first text after 3.81% and Speechmatics Linden after 3.93%, at the median.

Test your voice agent the same way.

Cekura runs these simulated calls on your agent and scores every one.