GPT-4o Mini Transcribe vs GPT-4o Transcribe
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- 4o Mini Transcribe3.35% · 630ms
- 4o Transcribe3.90% · 652ms
GPT-4o Mini Transcribe is ahead of GPT-4o Transcribe on both datasets together, the Ocular Dataset and final-text delay. The Pipecat Dataset is too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER3.73%6.85%
- Pipecat Dataset WER3.35%3.90%
- Ocular Dataset WER4.45%12.45%
- Time to first textn/an/a
- Final-text delay630ms652ms
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 4o Transcribe FAQ
Which is more accurate, GPT-4o Mini Transcribe or GPT-4o Transcribe?
GPT-4o Mini Transcribe is more accurate on the public clips. On the 1,000 public Pipecat clips, GPT-4o Mini Transcribe scores 3.73% and GPT-4o Transcribe 6.85%, so GPT-4o Mini Transcribe makes fewer errors by 3.12 points. On the eight licensed Ocular recordings, GPT-4o Mini Transcribe scores 3.35% and GPT-4o Transcribe 3.90%, with likely ranges of 3.08 to 3.65% and 3.43 to 4.42%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
GPT-4o Mini Transcribe is more accurate on the public clips. On the 1,000 public Pipecat clips, GPT-4o Mini Transcribe scores 3.73% and GPT-4o Transcribe 6.85%, so GPT-4o Mini Transcribe makes fewer errors by 3.12 points. On the eight licensed Ocular recordings, GPT-4o Mini Transcribe scores 3.35% and GPT-4o Transcribe 3.90%, with likely ranges of 3.08 to 3.65% and 3.43 to 4.42%. The ranges overlap, so the difference is too close to call. 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.
GPT-4o Mini Transcribe and GPT-4o Transcribe are level on the two figures a voice agent depends on most. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
No. Neither returns text until the speaker stops, so both are judged on how soon the final transcript arrives.
Test your voice agent the same way.
Cekura runs these simulated calls on your agent and scores every one.