Google Chirp 2 vs GPT-4o Mini Transcribe
Google Chirp 2 is ahead of GPT-4o Mini Transcribe on the Pipecat Dataset and final-text delay. The Ocular Dataset is too close to call.
Google Chirp 2 has a newer release. See Google Chirp 3 vs GPT-4o Mini Transcribe.
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
Google Chirp 2 is the better pick over GPT-4o Mini Transcribe on every measure that separates them: accuracy on clean, scripted audio (0.76 points lower) and quick turn-taking once the caller stops (62ms 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 2
- 2.59%9th
- GPT-4o Mini Transcribe
- 3.35%11th
Google Chirp 2, 0.76 points lower
- Google Chirp 2
- 3.80%5th
- GPT-4o Mini Transcribe
- 4.45%12th
Too close to call: inside the margin of error
- Google Chirp 2
- 4.50s15th
- GPT-4o Mini Transcribe
- No text until the speaker stops
Not comparable
- Google Chirp 2
- 568ms15th
- GPT-4o Mini Transcribe
- 630ms16th
Google Chirp 2, 62ms 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 GPT-4o Mini Transcribe shows first text after 40.84s and final text after 1.53s, 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 |
| GPT-4o Mini Transcribe | No text until the speaker stops | |||
| Final-text delay | Google Chirp 2 | 568ms* | 1.04s* | 1.22s* |
| GPT-4o Mini Transcribe | 630ms | 1.34s | 1.53s | |
- 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 | 4o Mini Transcribe |
|---|---|---|
| Pipecat Dataset WER | 2.59%9th of 17 | 3.35%11th of 17 |
| Ocular Dataset WER | 3.80%5th of 17 | 4.45%12th of 17 |
| Time to first text | 4.50s15th of 15 | Not comparable |
| Final-text delay | 568ms15th of 17 | 630ms16th 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 |
| GPT-4o Mini Transcribe | 1,000 | 8 | 206 | 0 |
Only clips with usable text count, so the two totals can differ. How WER is scored.
Related comparisons
Both providers, every model: Google vs OpenAI
- Google Chirp 2 vs Google Chirp 3
- GPT-4o Mini Transcribe vs Deepgram Nova-3
- GPT-4o Mini Transcribe vs Smallest Pulse
- GPT-4o Mini Transcribe vs GPT-4o Transcribe
- GPT-4o Mini Transcribe vs Deepgram Flux English
- GPT-4o Mini Transcribe vs Inworld STT-1
- GPT-4o Mini Transcribe vs Soniox STT-RT v5
- GPT-4o Mini Transcribe vs Speechmatics Linden
- GPT-4o Mini Transcribe vs Cartesia Ink 2
- GPT-4o Mini Transcribe vs GPT Realtime Whisper
- GPT-4o Mini Transcribe vs Reson8
- GPT-4o Mini Transcribe vs Google Chirp 3
- GPT-4o Mini Transcribe vs AssemblyAI Universal 3.6 Pro
- GPT-4o Mini Transcribe vs Deepgram Flux Multilingual
- GPT-4o Mini Transcribe vs Gradium
Frequently asked questions
Which is more accurate, Google Chirp 2 or GPT-4o Mini Transcribe?
Google Chirp 2 is more accurate on the public clips. On the 1,000 public Pipecat clips, Google Chirp 2 scores 2.59% and GPT-4o Mini Transcribe 3.35%, so Google Chirp 2 makes fewer errors by 0.76 points. On the eight licensed Ocular recordings, Google Chirp 2 scores 3.80% and GPT-4o Mini Transcribe 4.45%, with likely ranges of 2.93 to 4.60% and 3.22 to 5.55%. 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 GPT-4o Mini Transcribe?
Yes. Google Chirp 2 finishes the transcript 62ms sooner. Google Chirp 2 has the final transcript 568ms after the speaker stops and GPT-4o Mini Transcribe 630ms, at the median. Both are measured on the same 206 streamed turns.
Is Google Chirp 2 or GPT-4o Mini Transcribe better for voice agents?
Google Chirp 2 finishes the transcript 62ms 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 GPT-4o Mini Transcribe stream text while the speaker is talking?
Only Google Chirp 2. GPT-4o Mini Transcribe returns no text until the speaker stops, which matters if your agent reacts to partial transcripts.