Google Chirp 2 vs Inworld STT-1
Inworld STT-1 is ahead of Google Chirp 2 on time to first text and final-text delay. The Pipecat Dataset and The Ocular Dataset are too close to call.
Google Chirp 2 has a newer release. See Google Chirp 3 vs Inworld STT-1.
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
Inworld STT-1 is the better pick over Google Chirp 2 on every measure that separates them: showing words while the caller is still talking (3.43s sooner) and quick turn-taking once the caller stops (527ms sooner). For accuracy on clean, scripted audio and 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 2
- 2.59%9th
- Inworld STT-1
- 2.72%10th
Too close to call: inside the margin of error
- Google Chirp 2
- 3.80%5th
- Inworld STT-1
- 10.60%16th
Too close to call: inside the margin of error
- Google Chirp 2
- 4.50s15th
- Inworld STT-1
- 1.06s6th
Inworld STT-1, 3.43s sooner
- Google Chirp 2
- 568ms15th
- Inworld STT-1
- 41ms2nd
Inworld STT-1, 527ms 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 2 shows first text after 8.15s and final text after 1.22s, and Inworld STT-1 shows first text after 1.07s and final text after 65ms, on a bad turn (P95) across the same streamed turns.
| Measure | Model | P50 | P90 | P95 |
|---|---|---|---|---|
| Time to first text | Google Chirp 2 | 4.50s | 6.40s | 8.15s |
| Inworld STT-1 | 1.06s | 1.07s | 1.07s | |
| Final-text delay | Google Chirp 2 | 568ms* | 1.04s* | 1.22s* |
| Inworld STT-1 | 41ms | 60ms | 65ms |
- 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 2 | STT-1 |
|---|---|---|
| Pipecat Dataset WER | 2.59%9th of 17 | 2.72%10th of 17 |
| Ocular Dataset WER | 3.80%5th of 17 | 10.60%16th of 17 |
| Time to first text | 4.50s15th of 15 | 1.06s6th of 15 |
| Final-text delay | 568ms15th of 17 | 41ms2nd of 17 |
How much audio each model was tested on
| Model | Pipecat clips | Ocular recordings | Turns timed | Failed |
|---|---|---|---|---|
| Google Chirp 2 | 1,000 | 8 | 205 | 1 |
| Inworld STT-1 | 1,000 | 8 | 206 | 0 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
- Google Chirp 2 vs Google Chirp 3
- Inworld STT-1 vs Soniox STT-RT v5
- Inworld STT-1 vs Speechmatics Linden
- Inworld STT-1 vs Cartesia Ink 2
- Inworld STT-1 vs GPT Realtime Whisper
- Inworld STT-1 vs Reson8
- Inworld STT-1 vs GPT-4o Mini Transcribe
- Inworld STT-1 vs Google Chirp 3
- Inworld STT-1 vs Deepgram Nova-3
- Inworld STT-1 vs Smallest Pulse
- Inworld STT-1 vs AssemblyAI Universal 3.6 Pro
- Inworld STT-1 vs GPT-4o Transcribe
- Inworld STT-1 vs Deepgram Flux English
- Inworld STT-1 vs Deepgram Flux Multilingual
- Inworld STT-1 vs Gradium
Frequently asked questions
Which is more accurate, Google Chirp 2 or Inworld STT-1?
Google Chirp 2 and Inworld STT-1 are too close to call on accuracy. On the 1,000 public Pipecat clips, Google Chirp 2 scores 2.59% and Inworld STT-1 2.72%, with likely ranges of 2.31 to 2.89% and 1.67 to 4.68%. The ranges overlap, so the difference is too close to call. On the eight licensed Ocular recordings, Google Chirp 2 scores 3.80% and Inworld STT-1 10.60%, with likely ranges of 2.93 to 4.60% and 3.85 to 22.76%. 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 2 faster than Inworld STT-1?
No. Inworld STT-1 finishes the transcript 527ms sooner. Google Chirp 2 has the final transcript 568ms after the speaker stops and Inworld STT-1 41ms, at the median. Both are measured on the same 206 streamed turns.
Is Google Chirp 2 or Inworld STT-1 better for voice agents?
Inworld STT-1 finishes the transcript 527ms 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 2 and Inworld STT-1 stream text while the speaker is talking?
Yes, both return partial text before the speaker stops. Google Chirp 2 shows first text after 4.50s and Inworld STT-1 after 1.06s, at the median, so Inworld STT-1 is 3.43s sooner.