GPT Realtime Whisper vs Smallest Pulse
Smallest Pulse is ahead on time to first text and final-text delay, and GPT Realtime Whisper on the Pipecat Dataset. 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
Pick GPT Realtime Whisper for accuracy on clean, scripted audio (1.50 points lower). Pick Smallest Pulse for showing words while the caller is still talking (322ms sooner) and quick turn-taking once the caller stops (342ms 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 Realtime Whisper
- 2.16%5th
- Smallest Pulse
- 3.66%13th
GPT Realtime Whisper, 1.50 points lower
- GPT Realtime Whisper
- 3.53%4th
- Smallest Pulse
- 3.46%3rd
Too close to call: inside the margin of error
- GPT Realtime Whisper
- 1.38s10th
- Smallest Pulse
- 1.06s5th
Smallest Pulse, 322ms sooner
- GPT Realtime Whisper
- 543ms14th
- Smallest Pulse
- 201ms10th
Smallest Pulse, 342ms 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 Realtime Whisper shows first text after 2.86s and final text after 669ms, and Smallest Pulse shows first text after 3.03s and final text after 773ms, on a bad turn (P95) across the same streamed turns.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | GPT Realtime Whisper | 1.38s | 1.84s | 2.86s |
| Smallest Pulse | 1.06s | 2.25s | 3.03s | |
| Final-text delay | GPT Realtime Whisper | 543ms | 647ms | 669ms |
| Smallest Pulse | 201ms | 356ms | 773ms |
- 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 | Realtime Whisper | Pulse |
|---|---|---|
| Pipecat Dataset WER | 2.16%5th of 17 | 3.66%13th of 17 |
| Ocular Dataset WER | 3.53%4th of 17 | 3.46%3rd of 17 |
| Time to first text | 1.38s10th of 15 | 1.06s5th of 15 |
| Final-text delay | 543ms14th of 17 | 201ms10th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| GPT Realtime Whisper | 1,000 | 8 | 206 | 0 |
| Smallest Pulse | 1,000 | 8 | 206 | 0 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
- 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 GPT-4o Transcribe
- GPT Realtime Whisper vs Deepgram Flux English
- GPT Realtime Whisper vs Deepgram Flux Multilingual
- GPT Realtime Whisper vs Gradium
- Smallest Pulse vs Deepgram Nova-3
- Smallest Pulse vs GPT-4o Transcribe
- Smallest Pulse vs Deepgram Flux English
- Smallest Pulse vs GPT-4o Mini Transcribe
- Smallest Pulse vs Inworld STT-1
- Smallest Pulse vs Soniox STT-RT v5
- Smallest Pulse vs Speechmatics Linden
- Smallest Pulse vs Cartesia Ink 2
- Smallest Pulse vs Deepgram Flux Multilingual
- Smallest Pulse vs Reson8
- Smallest Pulse vs Google Chirp 3
- Smallest Pulse vs AssemblyAI Universal 3.6 Pro
- Smallest Pulse vs Gradium
Frequently asked questions
Which is more accurate, GPT Realtime Whisper or Smallest Pulse?
GPT Realtime Whisper is more accurate on the public clips. On the 1,000 public Pipecat clips, GPT Realtime Whisper scores 2.16% and Smallest Pulse 3.66%, so GPT Realtime Whisper makes fewer errors by 1.50 points. On the eight licensed Ocular recordings, GPT Realtime Whisper scores 3.53% and Smallest Pulse 3.46%, with likely ranges of 2.58 to 4.51% and 2.66 to 4.22%. 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 Realtime Whisper faster than Smallest Pulse?
No. Smallest Pulse finishes the transcript 342ms sooner. GPT Realtime Whisper has the final transcript 543ms after the speaker stops and Smallest Pulse 201ms, at the median. Both are measured on the same 206 streamed turns.
Is GPT Realtime Whisper or Smallest Pulse better for voice agents?
Smallest Pulse finishes the transcript 342ms 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 Realtime Whisper and Smallest Pulse stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. GPT Realtime Whisper shows first text after 1.38s and Smallest Pulse after 1.06s, at the median, so Smallest Pulse is 322ms sooner.