Gradium vs GPT Realtime Whisper
GPT Realtime Whisper is ahead on the Pipecat Dataset and time to first text, and Gradium on 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
Pick Gradium for quick turn-taking once the caller stops (331ms sooner). Pick GPT Realtime Whisper for accuracy on clean, scripted audio (4.32 points lower) and showing words while the caller is still talking (326ms 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
- Gradium
- 6.48%17th
- GPT Realtime Whisper
- 2.16%5th
GPT Realtime Whisper, 4.32 points lower
- Gradium
- 4.45%12th
- GPT Realtime Whisper
- 3.53%4th
Too close to call: inside the margin of error
- Gradium
- 1.71s12th
- GPT Realtime Whisper
- 1.38s10th
GPT Realtime Whisper, 326ms sooner
- Gradium
- 212ms11th
- GPT Realtime Whisper
- 543ms14th
Gradium, 331ms 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
Gradium shows first text after 7.32s and final text after 280ms, 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 | Gradium | 1.71s | 4.05s | 7.32s |
| GPT Realtime Whisper | 1.38s | 1.84s | 2.86s | |
| Final-text delay | Gradium | 212ms | 266ms | 280ms |
| 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 | Gradium | Realtime Whisper |
|---|---|---|
| Pipecat Dataset WER | 6.48%17th of 17 | 2.16%5th of 17 |
| Ocular Dataset WER | 4.45%12th of 17 | 3.53%4th of 17 |
| Time to first text | 1.71s12th of 15 | 1.38s10th of 15 |
| Final-text delay | 212ms11th of 17 | 543ms14th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Gradium | 1,000 | 8 | 198 | 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
- Gradium vs Deepgram Flux Multilingual
- Gradium vs Deepgram Flux English
- Gradium vs GPT-4o Transcribe
- Gradium vs Smallest Pulse
- Gradium vs Deepgram Nova-3
- Gradium vs GPT-4o Mini Transcribe
- Gradium vs Inworld STT-1
- Gradium vs Soniox STT-RT v5
- Gradium vs Speechmatics Linden
- Gradium vs Cartesia Ink 2
- Gradium vs Reson8
- Gradium vs Google Chirp 3
- Gradium vs AssemblyAI Universal 3.6 Pro
- 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 GPT-4o Transcribe
- GPT Realtime Whisper vs Deepgram Flux English
- GPT Realtime Whisper vs Deepgram Flux Multilingual
Frequently asked questions
Which is more accurate, Gradium or GPT Realtime Whisper?
GPT Realtime Whisper is more accurate on the public clips. On the 1,000 public Pipecat clips, Gradium scores 6.48% and GPT Realtime Whisper 2.16%, so GPT Realtime Whisper makes fewer errors by 4.32 points. On the eight licensed Ocular recordings, Gradium scores 4.45% and GPT Realtime Whisper 3.53%, with likely ranges of 3.17 to 5.90% 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 Gradium faster than GPT Realtime Whisper?
Yes. Gradium finishes the transcript 331ms sooner. Gradium has the final transcript 212ms after the speaker stops and GPT Realtime Whisper 543ms, at the median. Both are measured on the same 206 streamed turns.
Is Gradium or GPT Realtime Whisper better for voice agents?
Gradium finishes the transcript 331ms 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 Gradium and GPT Realtime Whisper stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Gradium shows first text after 1.71s and GPT Realtime Whisper after 1.38s, at the median, so GPT Realtime Whisper is 326ms sooner.