Google Chirp 3 vs GPT Realtime Whisper
Google Chirp 3 is ahead on final-text delay, and GPT Realtime Whisper on time to first text. 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
Pick Google Chirp 3 for quick turn-taking once the caller stops (68ms sooner). Pick GPT Realtime Whisper for showing words while the caller is still talking (3.10s 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
- Google Chirp 3
- 2.00%3rd
- GPT Realtime Whisper
- 2.16%5th
Too close to call: inside the margin of error
- Google Chirp 3
- 4.19%9th
- GPT Realtime Whisper
- 3.53%4th
Too close to call: inside the margin of error
- Google Chirp 3
- 4.48s14th
- GPT Realtime Whisper
- 1.38s10th
GPT Realtime Whisper, 3.10s sooner
- Google Chirp 3
- 475ms13th
- GPT Realtime Whisper
- 543ms14th
Google Chirp 3, 68ms 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
Google Chirp 3 shows first text after 7.97s and final text after 1.41s, 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 | Google Chirp 3 | 4.48s | 6.21s | 7.97s |
| GPT Realtime Whisper | 1.38s | 1.84s | 2.86s | |
| Final-text delay | Google Chirp 3 | 475ms* | 941ms* | 1.41s* |
| 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.
* Final-text delay is the observed time after stream close, because controlled finalization is not available for this model. Compare it with care against models that finalize on request.
How each ranks among all 17 models
Place among the 17 models on each metric. Lower is better on all four.
| Metric | Chirp 3 | Realtime Whisper |
|---|---|---|
| Pipecat Dataset WER | 2.00%3rd of 17 | 2.16%5th of 17 |
| Ocular Dataset WER | 4.19%9th of 17 | 3.53%4th of 17 |
| Time to first text | 4.48s14th of 15 | 1.38s10th of 15 |
| Final-text delay | 475ms13th of 17 | 543ms14th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Google Chirp 3 | 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
Both providers, every model: Google vs OpenAI
- Google Chirp 3 vs Reson8
- Google Chirp 3 vs AssemblyAI Universal 3.6 Pro
- Google Chirp 3 vs Cartesia Ink 2
- Google Chirp 3 vs Speechmatics Linden
- Google Chirp 3 vs Soniox STT-RT v5
- Google Chirp 3 vs Google Chirp 2
- Google Chirp 3 vs Inworld STT-1
- Google Chirp 3 vs GPT-4o Mini Transcribe
- Google Chirp 3 vs Deepgram Nova-3
- Google Chirp 3 vs Smallest Pulse
- Google Chirp 3 vs GPT-4o Transcribe
- Google Chirp 3 vs Deepgram Flux English
- Google Chirp 3 vs Deepgram Flux Multilingual
- Google Chirp 3 vs Gradium
- GPT Realtime Whisper vs Reson8
- 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
- GPT Realtime Whisper vs Gradium
Frequently asked questions
Which is more accurate, Google Chirp 3 or GPT Realtime Whisper?
Google Chirp 3 and GPT Realtime Whisper are too close to call on accuracy. On the 1,000 public Pipecat clips, Google Chirp 3 scores 2.00% and GPT Realtime Whisper 2.16%, with likely ranges of 1.77 to 2.25% and 1.92 to 2.41%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Google Chirp 3 scores 4.19% and GPT Realtime Whisper 3.53%, with likely ranges of 2.97 to 5.27% 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 Google Chirp 3 faster than GPT Realtime Whisper?
Yes. Google Chirp 3 finishes the transcript 68ms sooner. Google Chirp 3 has the final transcript 475ms after the speaker stops and GPT Realtime Whisper 543ms, at the median. Both are measured on the same 206 streamed turns.
Is Google Chirp 3 or GPT Realtime Whisper better for voice agents?
Google Chirp 3 finishes the transcript 68ms 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 Google Chirp 3 and GPT Realtime Whisper stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Google Chirp 3 shows first text after 4.48s and GPT Realtime Whisper after 1.38s, at the median, so GPT Realtime Whisper is 3.10s sooner.