GPT-4o Mini Transcribe vs GPT Realtime Whisper
GPT Realtime Whisper is ahead of GPT-4o Mini Transcribe on the Pipecat Dataset and final-text delay. The Ocular Dataset is too close to call.
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 Mini Transcribe on every measure that separates them: accuracy on clean, scripted audio (1.20 points lower) and quick turn-taking once the caller stops (87ms sooner). For accuracy on real phone conversations, the gap is inside the margin of error, so neither is ahead.
The four metrics, side by side
- GPT-4o Mini Transcribe
- 3.35%11th
- GPT Realtime Whisper
- 2.16%5th
GPT Realtime Whisper, 1.20 points lower
- GPT-4o Mini Transcribe
- 4.45%12th
- GPT Realtime Whisper
- 3.53%4th
Too close to call: inside the margin of error
- GPT-4o Mini Transcribe
- No text until the speaker stops
- GPT Realtime Whisper
- 1.38s10th
Not comparable
- GPT-4o Mini Transcribe
- 630ms16th
- GPT Realtime Whisper
- 543ms14th
GPT Realtime Whisper, 87ms 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 Mini Transcribe shows first text after 40.84s and final text after 1.53s, 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 Mini Transcribe | No text until the speaker stops | ||
| GPT Realtime Whisper | 1.38s | 1.84s | 2.86s | |
| Final-text delay | GPT-4o Mini Transcribe | 630ms | 1.34s | 1.53s |
| 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 Mini Transcribe | Realtime Whisper |
|---|---|---|
| Pipecat Dataset WER | 3.35%11th of 17 | 2.16%5th of 17 |
| Ocular Dataset WER | 4.45%12th of 17 | 3.53%4th of 17 |
| Time to first text | Not comparable | 1.38s10th of 15 |
| Final-text delay | 630ms16th of 17 | 543ms14th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| GPT-4o Mini 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 Mini Transcribe vs Deepgram Nova-3
- GPT-4o Mini Transcribe vs Smallest Pulse
- GPT-4o Mini Transcribe vs GPT-4o Transcribe
- GPT-4o Mini Transcribe vs Deepgram Flux English
- GPT-4o Mini Transcribe vs Inworld STT-1
- GPT-4o Mini Transcribe vs Soniox STT-RT v5
- GPT-4o Mini Transcribe vs Speechmatics Linden
- GPT-4o Mini Transcribe vs Cartesia Ink 2
- GPT-4o Mini Transcribe vs Reson8
- GPT-4o Mini Transcribe vs Google Chirp 3
- GPT-4o Mini Transcribe vs AssemblyAI Universal 3.6 Pro
- GPT-4o Mini Transcribe vs Deepgram Flux Multilingual
- GPT-4o Mini 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 Deepgram Nova-3
- GPT Realtime Whisper vs Smallest Pulse
- GPT Realtime Whisper vs GPT-4o Transcribe
- 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 Mini Transcribe or GPT Realtime Whisper?
GPT Realtime Whisper is more accurate on the public clips. On the 1,000 public Pipecat clips, GPT-4o Mini Transcribe scores 3.35% and GPT Realtime Whisper 2.16%, so GPT Realtime Whisper makes fewer errors by 1.20 points. On the eight licensed Ocular recordings, GPT-4o Mini Transcribe scores 4.45% and GPT Realtime Whisper 3.53%, with likely ranges of 3.22 to 5.55% and 2.58 to 4.51%. The ranges overlap, so the difference is too close to call. Word error rate counts incorrect, missing, and extra words, so lower is better.
Is GPT-4o Mini Transcribe faster than GPT Realtime Whisper?
No. GPT Realtime Whisper finishes the transcript 87ms sooner. GPT-4o Mini Transcribe has the final transcript 630ms after the speaker stops and GPT Realtime Whisper 543ms, at the median. Both are measured on the same 206 streamed turns.
Is GPT-4o Mini Transcribe or GPT Realtime Whisper better for voice agents?
GPT Realtime Whisper finishes the transcript 87ms sooner, and the two are too close to call on real conversations. A voice agent cannot reply until the final transcript arrives, and the Ocular recordings are real conversations.
Do GPT-4o Mini Transcribe and GPT Realtime Whisper stream text while the speaker is talking?
Only GPT Realtime Whisper. GPT-4o Mini Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.