Deepgram Nova-3 vs Google Chirp 2
Deepgram Nova-3 is ahead on time to first text and final-text delay, and Google Chirp 2 on the Pipecat Dataset. The Ocular Dataset is too close to call.
Google Chirp 2 has a newer release. See Deepgram Nova-3 vs Google Chirp 3.
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 Deepgram Nova-3 for showing words while the caller is still talking (3.43s sooner) and quick turn-taking once the caller stops (465ms sooner). Pick Google Chirp 2 for accuracy on clean, scripted audio (0.87 points lower). For accuracy on real phone conversations, the gap is inside the margin of error, so neither is ahead.
The four metrics, side by side
- Deepgram Nova-3
- 3.46%12th
- Google Chirp 2
- 2.59%9th
Google Chirp 2, 0.87 points lower
- Deepgram Nova-3
- 4.39%11th
- Google Chirp 2
- 3.80%5th
Too close to call: inside the margin of error
- Deepgram Nova-3
- 1.06s7th
- Google Chirp 2
- 4.50s15th
Deepgram Nova-3, 3.43s sooner
- Deepgram Nova-3
- 103ms4th
- Google Chirp 2
- 568ms15th
Deepgram Nova-3, 465ms 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
Deepgram Nova-3 shows first text after 2.07s and final text after 155ms, and Google Chirp 2 shows first text after 8.15s and final text after 1.22s, on a bad turn (P95) across the same streamed turns.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | Deepgram Nova-3 | 1.06s | 1.10s | 2.07s |
| Google Chirp 2 | 4.50s | 6.40s | 8.15s | |
| Final-text delay | Deepgram Nova-3 | 103ms | 143ms | 155ms |
| Google Chirp 2 | 568ms* | 1.04s* | 1.22s* |
- 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 | Nova-3 | Chirp 2 |
|---|---|---|
| Pipecat Dataset WER | 3.46%12th of 17 | 2.59%9th of 17 |
| Ocular Dataset WER | 4.39%11th of 17 | 3.80%5th of 17 |
| Time to first text | 1.06s7th of 15 | 4.50s15th of 15 |
| Final-text delay | 103ms4th of 17 | 568ms15th of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Deepgram Nova-3 | 1,000 | 8 | 202 | 0 |
| Google Chirp 2 | 1,000 | 8 | 205 | 1 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
Both providers, every model: Deepgram vs Google
- Deepgram Nova-3 vs GPT-4o Mini Transcribe
- Deepgram Nova-3 vs Smallest Pulse
- Deepgram Nova-3 vs GPT-4o Transcribe
- Deepgram Nova-3 vs Deepgram Flux English
- Deepgram Nova-3 vs Inworld STT-1
- Deepgram Nova-3 vs Soniox STT-RT v5
- Deepgram Nova-3 vs Speechmatics Linden
- Deepgram Nova-3 vs Cartesia Ink 2
- Deepgram Nova-3 vs GPT Realtime Whisper
- Deepgram Nova-3 vs Reson8
- Deepgram Nova-3 vs Google Chirp 3
- Deepgram Nova-3 vs Deepgram Flux Multilingual
- Deepgram Nova-3 vs AssemblyAI Universal 3.6 Pro
- Deepgram Nova-3 vs Gradium
- Google Chirp 2 vs Google Chirp 3
Frequently asked questions
Which is more accurate, Deepgram Nova-3 or Google Chirp 2?
Google Chirp 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Deepgram Nova-3 scores 3.46% and Google Chirp 2 2.59%, so Google Chirp 2 makes fewer errors by 0.87 points. On the eight licensed Ocular recordings, Deepgram Nova-3 scores 4.39% and Google Chirp 2 3.80%, with likely ranges of 3.42 to 5.25% and 2.93 to 4.60%. 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 Deepgram Nova-3 faster than Google Chirp 2?
Yes. Deepgram Nova-3 finishes the transcript 465ms sooner. Deepgram Nova-3 has the final transcript 103ms after the speaker stops and Google Chirp 2 568ms, at the median. Both are measured on the same 206 streamed turns.
Is Deepgram Nova-3 or Google Chirp 2 better for voice agents?
Deepgram Nova-3 finishes the transcript 465ms 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 Deepgram Nova-3 and Google Chirp 2 stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Deepgram Nova-3 shows first text after 1.06s and Google Chirp 2 after 4.50s, at the median, so Deepgram Nova-3 is 3.43s sooner.