Inworld STT-1 vs GPT-4o Transcribe
Accuracy and speed
Left gets fewer words wrong. Lower has the final text ready sooner.
- STT-12.72% · 41ms
- 4o Transcribe3.90% · 652ms
Inworld STT-1 is ahead of GPT-4o Transcribe on both datasets together and final-text delay. The Pipecat Dataset and The Ocular Dataset are too close to call.
Last updated Methodology by Dileep Chagam
Who is better at what
- Overall WER5.44%6.85%
- Pipecat Dataset WER2.72%3.90%
- Ocular Dataset WER10.60%12.45%
- Time to first text1.06sn/a
- Final-text delay41ms652ms
Lower is better on every measure. Too close to call means the likely ranges overlap. Our guide explains how word error rate is measured.
STT-1 vs 4o Transcribe FAQ
Which is more accurate, Inworld STT-1 or GPT-4o Transcribe?
Inworld STT-1 is more accurate on the public clips. On the 1,000 public Pipecat clips, Inworld STT-1 scores 5.44% and GPT-4o Transcribe 6.85%, so Inworld STT-1 makes fewer errors by 1.41 points. On the eight licensed Ocular recordings, Inworld STT-1 scores 2.72% and GPT-4o Transcribe 3.90%, with likely ranges of 1.67 to 4.68% 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.
Inworld STT-1 is more accurate on the public clips. On the 1,000 public Pipecat clips, Inworld STT-1 scores 5.44% and GPT-4o Transcribe 6.85%, so Inworld STT-1 makes fewer errors by 1.41 points. On the eight licensed Ocular recordings, Inworld STT-1 scores 2.72% and GPT-4o Transcribe 3.90%, with likely ranges of 1.67 to 4.68% 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.
Inworld STT-1 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.
Only Inworld STT-1. GPT-4o 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.