GPT-4o Transcribe vs GPT Realtime Whisper
GPT Realtime Whisper is ahead of GPT-4o Transcribe on the Pipecat Dataset, the Ocular Dataset and final-text delay.
Last updated Methodology by Dileep Chagam
Accuracy vs speed
Each dot is one model. Bottom-left is best: fewer errors and a faster final transcript.
Which to pick
GPT Realtime Whisper is the better pick over GPT-4o Transcribe on every measure that separates them: accuracy on clean, scripted audio (1.75 points lower), accuracy on real phone conversations (8.92 points lower) and quick turn-taking once the caller stops (109ms sooner).
The four metrics, side by side
- GPT-4o Transcribe
- 3.90%14th
- GPT Realtime Whisper
- 2.16%5th
GPT Realtime Whisper, 1.75 points lower
- GPT-4o Transcribe
- 12.45%17th
- GPT Realtime Whisper
- 3.53%4th
GPT Realtime Whisper, 8.92 points lower
- GPT-4o Transcribe
- No text until the speaker stops
- GPT Realtime Whisper
- 1.38s10th
Not comparable
- GPT-4o Transcribe
- 652ms17th
- GPT Realtime Whisper
- 543ms14th
GPT Realtime Whisper, 109ms sooner
Lower is better on every metric. The small figure is each model's place in the whole field. What each metric measures.
- WER · Word error rate
- Share of words the model got wrong: replaced, missing or added. Lower is better.
- Pipecat Dataset
- 1,000 short public clips from Pipecat's STT benchmark dataset.
- Ocular Dataset
- 8 recordings from 4 real phone conversations, licensed from Ocular.
- TTFT · Time to first text
- How long after the audio starts streaming until the first words appear.
- TTFS · Final-text delay
- How long after the caller stops until the full transcript arrives. A voice agent waits for this before it replies.
First text and final text, at three percentiles
GPT-4o Transcribe shows first text after 40.63s and final text after 1.97s, and GPT Realtime Whisper shows first text after 2.86s and final text after 669ms, on a bad turn (P95) across the same streamed turns.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | GPT-4o Transcribe | No text until the speaker stops | ||
| GPT Realtime Whisper | 1.38s | 1.84s | 2.86s | |
| Final-text delay | GPT-4o Transcribe | 652ms | 1.73s | 1.97s |
| GPT Realtime Whisper | 543ms | 647ms | 669ms | |
- P50 / P90 / P95 · Typical, slow and slowest turns
- Half of turns are faster than P50. Only 1 in 10 is slower than P90, and 1 in 20 slower than P95.
How each ranks among all 17 models
Place among the 17 models on each metric. Lower is better on all four.
| Metric | 4o Transcribe | Realtime Whisper |
|---|---|---|
| Pipecat Dataset WER | 3.90%14th of 17 | 2.16%5th of 17 |
| Ocular Dataset WER | 12.45%17th of 17 | 3.53%4th of 17 |
| Time to first text | Not comparable | 1.38s10th of 15 |
| Final-text delay | 652ms17th of 17 | 543ms14th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| GPT-4o Transcribe | 1,000 | 8 | 206 | 0 |
| GPT Realtime Whisper | 1,000 | 8 | 206 | 0 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
- GPT-4o Transcribe vs Deepgram Flux English
- GPT-4o Transcribe vs Smallest Pulse
- GPT-4o Transcribe vs Deepgram Nova-3
- GPT-4o Transcribe vs GPT-4o Mini Transcribe
- GPT-4o Transcribe vs Deepgram Flux Multilingual
- GPT-4o Transcribe vs Inworld STT-1
- GPT-4o Transcribe vs Soniox STT-RT v5
- GPT-4o Transcribe vs Speechmatics Linden
- GPT-4o Transcribe vs Cartesia Ink 2
- GPT-4o Transcribe vs Reson8
- GPT-4o Transcribe vs Google Chirp 3
- GPT-4o Transcribe vs AssemblyAI Universal 3.6 Pro
- GPT-4o Transcribe vs Gradium
- GPT Realtime Whisper vs Reson8
- GPT Realtime Whisper vs Google Chirp 3
- GPT Realtime Whisper vs Cartesia Ink 2
- GPT Realtime Whisper vs Speechmatics Linden
- GPT Realtime Whisper vs AssemblyAI Universal 3.6 Pro
- GPT Realtime Whisper vs Soniox STT-RT v5
- GPT Realtime Whisper vs Inworld STT-1
- GPT Realtime Whisper vs GPT-4o Mini Transcribe
- GPT Realtime Whisper vs Deepgram Nova-3
- GPT Realtime Whisper vs Smallest Pulse
- GPT Realtime Whisper vs Deepgram Flux English
- GPT Realtime Whisper vs Deepgram Flux Multilingual
- GPT Realtime Whisper vs Gradium
Frequently asked questions
Which is more accurate, GPT-4o Transcribe or GPT Realtime Whisper?
GPT Realtime Whisper is more accurate on both datasets. On the 1,000 public Pipecat clips, GPT-4o Transcribe scores 3.90% and GPT Realtime Whisper 2.16%, so GPT Realtime Whisper makes fewer errors by 1.75 points. On the eight licensed Ocular recordings, GPT-4o Transcribe scores 12.45% and GPT Realtime Whisper 3.53%, so GPT Realtime Whisper makes fewer errors by 8.92 points. Word error rate counts incorrect, missing, and extra words, so lower is better.
Is GPT-4o Transcribe faster than GPT Realtime Whisper?
No. GPT Realtime Whisper finishes the transcript 109ms sooner. GPT-4o Transcribe has the final transcript 652ms after the speaker stops and GPT Realtime Whisper 543ms, at the median. Both are measured on the same 206 streamed turns.
Is GPT-4o Transcribe or GPT Realtime Whisper better for voice agents?
GPT Realtime Whisper is the stronger pick for voice agents: it makes fewer errors on real conversations and finishes the transcript 109ms sooner. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Do GPT-4o Transcribe and GPT Realtime Whisper stream text while the speaker is talking?
Only GPT Realtime Whisper. GPT-4o Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.