GPT-4o Mini Transcribe vs Reson8
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- 4o Mini Transcribe3.35% · 630ms
- Reson82.10% · 235ms
Reson8 is ahead of GPT-4o Mini Transcribe on both datasets together, the Pipecat Dataset and final-text delay. The Ocular Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.73%2.38%
- Pipecat Dataset WER3.35%2.10%
- Ocular Dataset WER4.45%2.93%
- Time to first textn/a2.40s
- Final-text delay630ms235ms
Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide covers testing OpenAI Realtime API voice agents.
4o Mini Transcribe vs Reson8 FAQ
Which is more accurate, GPT-4o Mini Transcribe or Reson8?
Reson8 is more accurate on both datasets. On the 1,000 public Pipecat clips, GPT-4o Mini Transcribe scores 3.73% and Reson8 2.38%, so Reson8 makes fewer errors by 1.35 points. On the eight licensed Ocular recordings, GPT-4o Mini Transcribe scores 3.35% and Reson8 2.10%, so Reson8 makes fewer errors by 1.26 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Reson8 is more accurate on both datasets. On the 1,000 public Pipecat clips, GPT-4o Mini Transcribe scores 3.73% and Reson8 2.38%, so Reson8 makes fewer errors by 1.35 points. On the eight licensed Ocular recordings, GPT-4o Mini Transcribe scores 3.35% and Reson8 2.10%, so Reson8 makes fewer errors by 1.26 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Final-text delay was not measured for one or both, so speed cannot be compared. Both are measured on the same 206 streamed turns.
Reson8 makes fewer errors on real conversations, and the two are not separated on speed. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Only Reson8. GPT-4o Mini Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.