Google Chirp 3
Google Chirp 3 is 2nd of 15 on the Pipecat Dataset and 12th of 13 on time to first text.
- 2.00%
- Pipecat WER · 2nd
- 4.19%
- Ocular WER · 8th
- 4.48s
- First text · 12th
- 475ms
- Final text · 11th
Quality and speed frontier
Every model's error rate on the public clips, against how long its transcript takes to settle.
Google Chirp 3 against every other model
Open on the metric Google Chirp 3 places highest on, with the other three a tab away. Lower is better on all of them, so the order runs best first.
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.
First text and final text, at three percentiles
Measured on the same 206 streamed Ocular Dataset turns as every other model. P90 and P95 say what a caller meets on a bad turn, which a median hides.
| Measure | P50 | P90 | P95 |
|---|---|---|---|
| Time to first text | 4.48s | 6.21s | 7.97s |
| Final-text delay | 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.
Google Chirp 3 on the other two views
The same charts the benchmark page carries, with Google Chirp 3 ringed. Consistency across the two datasets is one reading; how fast a model starts against how fast it commits is the other.
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
- 1,000
- Pipecat clips scored
- 8
- Ocular recordings scored
- 206
- turns timed
- 0
- requests that failed
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
Where does Google Chirp 3 place in the benchmark?
Google Chirp 3 places highest on the Pipecat Dataset, 2nd of 15 at 2.00%. Its weakest placing is time to first text, 12th of 13 at 4.48s.
How accurate is Google Chirp 3?
Google Chirp 3 transcribes the 1,000 public Pipecat clips at 2.00% word error rate and the eight licensed Ocular recordings at 4.19%. Word error rate counts incorrect, missing, and extra words against the reference transcript, so lower is better.
How fast is Google Chirp 3 in a live conversation?
First text arrives after 4.48s at the median, and the transcript is final 475ms after the speaker stops. Both are measured on the same 206 streamed turns as every other model, and the page shows P90 and P95 as well, which is what a caller meets on a bad turn.
How was Google Chirp 3 measured?
Every model runs the same two datasets under the same conditions: 1,000 public clips from Pipecat's STT benchmark dataset for accuracy at scale, and eight licensed conversation recordings from Ocular for real speech. Latency comes from 206 streamed turns, using each provider's own supported finalization contract. Google Chirp 3 returned usable text for 1,000 of the public clips.