GPT Realtime Whisper vs Soniox STT-RT v5
Soniox STT-RT v5 is ahead of GPT Realtime Whisper on time to first text and final-text delay. The Pipecat Dataset and The Ocular Dataset are 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
Soniox STT-RT v5 is the better pick over GPT Realtime Whisper on every measure that separates them: showing words while the caller is still talking (184ms sooner) and quick turn-taking once the caller stops (505ms sooner). For accuracy on clean, scripted audio and 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
- Soniox STT-RT v5
- 2.54%8th
Too close to call: inside the margin of error
- GPT Realtime Whisper
- 3.53%4th
- Soniox STT-RT v5
- 3.92%6th
Too close to call: inside the margin of error
- GPT Realtime Whisper
- 1.38s10th
- Soniox STT-RT v5
- 1.20s9th
Soniox STT-RT v5, 184ms sooner
- GPT Realtime Whisper
- 543ms14th
- Soniox STT-RT v5
- 38ms1st
Soniox STT-RT v5, 505ms 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 Soniox STT-RT v5 shows first text after 1.71s and final text after 79ms, 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 |
| Soniox STT-RT v5 | 1.20s | 1.67s | 1.71s | |
| Final-text delay | GPT Realtime Whisper | 543ms | 647ms | 669ms |
| Soniox STT-RT v5 | 38ms | 72ms | 79ms |
- 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 | STT-RT v5 |
|---|---|---|
| Pipecat Dataset WER | 2.16%5th of 17 | 2.54%8th of 17 |
| Ocular Dataset WER | 3.53%4th of 17 | 3.92%6th of 17 |
| Time to first text | 1.38s10th of 15 | 1.20s9th of 15 |
| Final-text delay | 543ms14th of 17 | 38ms1st 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 |
| Soniox STT-RT v5 | 1,000 | 8 | 200 | 6 |
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 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 GPT-4o Transcribe
- GPT Realtime Whisper vs Deepgram Flux English
- GPT Realtime Whisper vs Deepgram Flux Multilingual
- GPT Realtime Whisper vs Gradium
- Soniox STT-RT v5 vs Speechmatics Linden
- Soniox STT-RT v5 vs Cartesia Ink 2
- Soniox STT-RT v5 vs Inworld STT-1
- Soniox STT-RT v5 vs Reson8
- Soniox STT-RT v5 vs Google Chirp 3
- Soniox STT-RT v5 vs AssemblyAI Universal 3.6 Pro
- Soniox STT-RT v5 vs GPT-4o Mini Transcribe
- Soniox STT-RT v5 vs Deepgram Nova-3
- Soniox STT-RT v5 vs Smallest Pulse
- Soniox STT-RT v5 vs GPT-4o Transcribe
- Soniox STT-RT v5 vs Deepgram Flux English
- Soniox STT-RT v5 vs Deepgram Flux Multilingual
- Soniox STT-RT v5 vs Gradium
Frequently asked questions
Which is more accurate, GPT Realtime Whisper or Soniox STT-RT v5?
GPT Realtime Whisper and Soniox STT-RT v5 are too close to call on accuracy. On the 1,000 public Pipecat clips, GPT Realtime Whisper scores 2.16% and Soniox STT-RT v5 2.54%, with likely ranges of 1.92 to 2.41% and 2.27 to 2.83%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, GPT Realtime Whisper scores 3.53% and Soniox STT-RT v5 3.92%, with likely ranges of 2.58 to 4.51% and 2.60 to 4.86%. 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 Soniox STT-RT v5?
No. Soniox STT-RT v5 finishes the transcript 505ms sooner. GPT Realtime Whisper has the final transcript 543ms after the speaker stops and Soniox STT-RT v5 38ms, at the median. Both are measured on the same 206 streamed turns.
Is GPT Realtime Whisper or Soniox STT-RT v5 better for voice agents?
Soniox STT-RT v5 finishes the transcript 505ms 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 Soniox STT-RT v5 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 Soniox STT-RT v5 after 1.20s, at the median, so Soniox STT-RT v5 is 184ms sooner.