Google Chirp 2 vs Google Chirp 3
Google Chirp 3 is ahead on the Pipecat Dataset, time to first text and final-text delay, and Google Chirp 2 on the Ocular Dataset.
Quality and speed frontier
Every model's error rate on the public clips, against how long its transcript takes to settle.
The four metrics, side by side
Word error rate on 1,000 clips from Pipecat's STT benchmark dataset.
- Google Chirp 2
- 2.59%7th
- Google Chirp 3
- 2.00%2nd
Google Chirp 3, 0.59 points lower
Word error rate on eight licensed recordings provided by Ocular.
- Google Chirp 2
- 3.80%5th
- Google Chirp 3
- 4.19%8th
Google Chirp 2, 0.39 points lower
Median delay before the first words arrive, from the first audio packet.
- Google Chirp 2
- 4.50s13th
- Google Chirp 3
- 4.48s12th
Google Chirp 3, 17ms sooner
Median delay after the speaker stops before the transcript is final.
- Google Chirp 2
- 568ms13th
- Google Chirp 3
- 475ms11th
Google Chirp 3, 93ms sooner
Lower is better on every metric. The small figure is each model's place in the whole field.
First text and final text, at three percentiles
Both measured on the same 206 streamed Ocular Dataset turns. P90 and P95 say what a caller meets on a bad turn, which a median hides.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | Google Chirp 2 | 4.50s | 6.40s | 8.15s |
| Google Chirp 3 | 4.48s | 6.21s | 7.97s | |
| Final-text delay | Google Chirp 2 | 568ms* | 1.04s* | 1.22s* |
| Google Chirp 3 | 475ms* | 941ms* | 1.41s* |
* 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.
Both against every other model
Open on the metric where the two sit furthest apart, with the other three a tab away.
Word error rate on 1,000 clips from Pipecat's STT benchmark dataset. Lower is better.
| # | Model | Pipecat Dataset | clips | |
|---|---|---|---|---|
| 1 | AssemblyAI Universal 3.5 Pro | 1.93% | 1,000 | |
| 2 | Google Chirp 3 | 2.00% | 1,000 | |
| 3 | Reson8 | 2.10% | 1,000 | |
| 4 | GPT Realtime Whisper | 2.16% | 1,000 | |
| 5 | Cartesia Ink 2 | 2.39% | 1,000 | |
| 6 | Speechmatics Linden | 2.46% | 998 | |
| 7 | Google Chirp 2 | 2.59% | 1,000 | |
| 8 | Inworld STT-1 | 2.72% | 1,000 | |
| 9 | GPT-4o Mini Transcribe | 3.35% | 1,000 | |
| 10 | Deepgram Nova-3 | 3.46% | 1,000 | |
| 11 | Smallest Pulse | 3.66% | 1,000 | |
| 12 | GPT-4o Transcribe | 3.90% | 1,000 | |
| 13 | Deepgram Flux English | 3.90% | 999 | |
| 14 | Deepgram Flux Multilingual | 4.96% | 999 | |
| 15 | Gradium | 6.48% | 1,000 |
Counts are the clips each model returned usable text for, so they differ between models and between datasets.
Both on the other two views
Pipecat vs Ocular accuracy
Every model's error rate on the public clips, against the same model on real conversations.
Transcription response time
How soon each model returns its first words, against how soon its transcript is final.
What the numbers rest on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Google Chirp 2 | 1,000 | 8 | 205 | 1 |
| Google Chirp 3 | 1,000 | 8 | 206 | 0 |
A clip counts only where the model returned usable text, so counts differ between models. Word error rate is measured the same way throughout: incorrect, missing, and extra words against the reference transcript.
Frequently asked questions
Is Google Chirp 2 or Google Chirp 3 more accurate?
On the 1,000 public Pipecat clips, Google Chirp 2 scores 2.59% and Google Chirp 3 2.00%, so Google Chirp 3 makes fewer errors by 0.59 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 3.80% and Google Chirp 3 4.19%, so Google Chirp 2 makes fewer errors by 0.39 points. The two datasets disagree, so the better choice depends on whether your audio looks more like clean public clips or real conversations.
Which is faster, Google Chirp 2 or Google Chirp 3?
Google Chirp 3 returns first text 17ms sooner, at 4.48s against 4.50s at the median. Google Chirp 3 has the final transcript 93ms sooner, 475ms after the speaker stops against 568ms. Both are measured on the same 206 streamed turns.
How were Google Chirp 2 and Google Chirp 3 compared?
Both ran the same two datasets under the same conditions as every other model in the benchmark: 1,000 public clips from Pipecat's STT benchmark dataset and eight licensed conversation recordings from Ocular. Google Chirp 2 returned usable text for 1,000 of the public clips and Google Chirp 3 for 1,000. Latency uses each provider's own supported finalization contract.