AssemblyAI Universal 3.5 Pro vs Google Chirp 2
AssemblyAI Universal 3.5 Pro 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.
- AssemblyAI Universal 3.5 Pro
- 1.93%1st
- Google Chirp 2
- 2.59%7th
AssemblyAI Universal 3.5 Pro, 0.66 points lower
Word error rate on eight licensed recordings provided by Ocular.
- AssemblyAI Universal 3.5 Pro
- 4.23%9th
- Google Chirp 2
- 3.80%5th
Google Chirp 2, 0.43 points lower
Median delay before the first words arrive, from the first audio packet.
- AssemblyAI Universal 3.5 Pro
- 489ms1st
- Google Chirp 2
- 4.50s13th
AssemblyAI Universal 3.5 Pro, 4.01s sooner
Median delay after the speaker stops before the transcript is final.
- AssemblyAI Universal 3.5 Pro
- 180ms7th
- Google Chirp 2
- 568ms13th
AssemblyAI Universal 3.5 Pro, 388ms 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 | AssemblyAI Universal 3.5 Pro | 489ms | 966ms | 1.08s |
| Google Chirp 2 | 4.50s | 6.40s | 8.15s | |
| Final-text delay | AssemblyAI Universal 3.5 Pro | 180ms | 532ms | 692ms |
| Google Chirp 2 | 568ms* | 1.04s* | 1.22s* |
* 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.
Time to first text, measured from the first audio packet. Lower is better.
| # | Model | First text | turns | |
|---|---|---|---|---|
| 1 | AssemblyAI Universal 3.5 Pro | 489ms | 205 | |
| 2 | Deepgram Flux English | 791ms | 199 | |
| 3 | Deepgram Flux Multilingual | 793ms | 175 | |
| 4 | Smallest Pulse | 1057ms | 206 | |
| 5 | Inworld STT-1 | 1063ms | 206 | |
| 6 | Deepgram Nova-3 | 1064ms | 203 | |
| 7 | Speechmatics Linden | 1190ms | 194 | |
| 8 | GPT Realtime Whisper | 1379ms | 206 | |
| 9 | Cartesia Ink 2 | 1511ms | 198 | |
| 10 | Gradium | 1705ms | 198 | |
| 11 | Reson8 | 2400ms | 201 | |
| 12 | Google Chirp 3 | 4480ms | 206 | |
| 13 | Google Chirp 2 | 4497ms | 205 |
Not ranked: GPT-4o Mini Transcribe and GPT-4o Transcribe return no text until the speaker stops, so first-text time is not comparable.
Median across the same 206 Ocular Dataset turns. Providers finalize differently, so compare models with similar finalization contracts before treating small gaps as meaningful.
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 |
|---|---|---|---|---|
| AssemblyAI Universal 3.5 Pro | 1,000 | 8 | 205 | 1 |
| Google Chirp 2 | 1,000 | 8 | 205 | 1 |
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 AssemblyAI Universal 3.5 Pro or Google Chirp 2 more accurate?
On the 1,000 public Pipecat clips, AssemblyAI Universal 3.5 Pro scores 1.93% and Google Chirp 2 2.59%, so AssemblyAI Universal 3.5 Pro makes fewer errors by 0.66 points. On the eight licensed Ocular recordings, AssemblyAI Universal 3.5 Pro scores 4.23% and Google Chirp 2 3.80%, so Google Chirp 2 makes fewer errors by 0.43 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, AssemblyAI Universal 3.5 Pro or Google Chirp 2?
AssemblyAI Universal 3.5 Pro returns first text 4.01s sooner, at 489ms against 4.50s at the median. AssemblyAI Universal 3.5 Pro has the final transcript 388ms sooner, 180ms after the speaker stops against 568ms. Both are measured on the same 206 streamed turns.
How were AssemblyAI Universal 3.5 Pro and Google Chirp 2 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. AssemblyAI Universal 3.5 Pro returned usable text for 1,000 of the public clips and Google Chirp 2 for 1,000. Latency uses each provider's own supported finalization contract.