Google Chirp 3 vs Gradium
Gradium is ahead on time to first text and final-text delay, and Google Chirp 3 on the Pipecat Dataset. The Ocular Dataset is 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 accuracy on clean, scripted audio (4.47 points lower). Pick Gradium for showing words while the caller is still talking (2.77s sooner) and quick turn-taking once the caller stops (263ms sooner). For 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
- Gradium
- 6.48%17th
Google Chirp 3, 4.47 points lower
- Google Chirp 3
- 4.19%9th
- Gradium
- 4.45%12th
Too close to call: inside the margin of error
- Google Chirp 3
- 4.48s14th
- Gradium
- 1.71s12th
Gradium, 2.77s sooner
- Google Chirp 3
- 475ms13th
- Gradium
- 212ms11th
Gradium, 263ms 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 Gradium shows first text after 7.32s and final text after 280ms, 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 |
| Gradium | 1.71s | 4.05s | 7.32s | |
| Final-text delay | Google Chirp 3 | 475ms* | 941ms* | 1.41s* |
| Gradium | 212ms | 266ms | 280ms |
- 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 | Gradium |
|---|---|---|
| Pipecat Dataset WER | 2.00%3rd of 17 | 6.48%17th of 17 |
| Ocular Dataset WER | 4.19%9th of 17 | 4.45%12th of 17 |
| Time to first text | 4.48s14th of 15 | 1.71s12th of 15 |
| Final-text delay | 475ms13th of 17 | 212ms11th 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 |
| Gradium | 1,000 | 8 | 198 | 0 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
- Google Chirp 3 vs Reson8
- Google Chirp 3 vs GPT Realtime Whisper
- 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
- Gradium vs Deepgram Flux Multilingual
- Gradium vs Deepgram Flux English
- Gradium vs GPT-4o Transcribe
- Gradium vs Smallest Pulse
- Gradium vs Deepgram Nova-3
- Gradium vs GPT-4o Mini Transcribe
- Gradium vs Inworld STT-1
- Gradium vs Soniox STT-RT v5
- Gradium vs Speechmatics Linden
- Gradium vs Cartesia Ink 2
- Gradium vs GPT Realtime Whisper
- Gradium vs Reson8
- Gradium vs AssemblyAI Universal 3.6 Pro
Frequently asked questions
Which is more accurate, Google Chirp 3 or Gradium?
Google Chirp 3 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 3 scores 2.00% and Gradium 6.48%, so Google Chirp 3 makes fewer errors by 4.47 points. On the eight licensed Ocular recordings, Google Chirp 3 scores 4.19% and Gradium 4.45%, with likely ranges of 2.97 to 5.27% and 3.17 to 5.90%. 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 Gradium?
No. Gradium finishes the transcript 263ms sooner. Google Chirp 3 has the final transcript 475ms after the speaker stops and Gradium 212ms, at the median. Both are measured on the same 206 streamed turns.
Is Google Chirp 3 or Gradium better for voice agents?
Gradium finishes the transcript 263ms 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 Gradium 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 Gradium after 1.71s, at the median, so Gradium is 2.77s sooner.