Google Speech-to-Text vs Whisper API on price
Google Speech-to-Text is cheaper for both recorded and live audio at every volume from 10 to 10,000 hours a month. At 100 hours a month, for recorded audio, Google Cloud's V2 dynamic batch costs $0.18 an hour against $0.36 for OpenAI's Whisper (whisper-1), 50% less; for live audio, Google Cloud's V1 with data logging costs $0.95 an hour against $1.02 for OpenAI's gpt-realtime-whisper, 7% less.
Each side's cheapest option at each volume, at regular pay-as-you-go prices; bold marks the cheaper. Price only: accuracy, languages and latency differ.
Recorded audio (batch)
| Audio a month | Google Speech-to-Text | Whisper API |
|---|---|---|
| 10 hours | $1.80 ($0.18/h) V2 dynamic batch | $3.60 ($0.36/h) Whisper (whisper-1) |
| 100 hours | $18 ($0.18/h) V2 dynamic batch | $36 ($0.36/h) Whisper (whisper-1) |
| 1,000 hours | $180 ($0.18/h) V2 dynamic batch | $360 ($0.36/h) Whisper (whisper-1) |
| 10,000 hours | $1,800 ($0.18/h) V2 dynamic batch | $3,600 ($0.36/h) Whisper (whisper-1) |
Live audio (streaming)
| Audio a month | Google Speech-to-Text | Whisper API |
|---|---|---|
| 10 hours | $8.64 ($0.864/h) V1 with data logging | $10.20 ($1.02/h) gpt-realtime-whisper |
| 100 hours | $95.04 ($0.95/h) V1 with data logging | $102 ($1.02/h) gpt-realtime-whisper |
| 1,000 hours | $959 ($0.959/h) V1 with data logging | $1,020 ($1.02/h) gpt-realtime-whisper |
| 10,000 hours | $9,000 ($0.90/h) V2 standard | $10,200 ($1.02/h) gpt-realtime-whisper |
What else changes the bill
| On the bill | Google Speech-to-Text | Whisper API |
|---|---|---|
| Free tier or credit | The V1 API's first 60 minutes a month are free; the V2 table lists no free minutes. New Google Cloud customers get $300 of free credit to try any Google Cloud product. | No free allowance or credit is listed on OpenAI's pricing page. |
| Billing | Billed per second: each request is rounded up to the nearest second. | OpenAI's pricing page doesn't say how partial minutes are counted. |
| Speaker labels, recorded audio | Not listed on the pricing page. | Through the separate gpt-4o-transcribe-diarize model, at the same estimated $0.006 a minute as gpt-4o-transcribe. |
| Speaker labels, live audio | Not listed on the pricing page. | Not listed on the pricing page. |
Not counted here: OpenAI's gpt-transcribe (batch, $0.27 an hour), OpenAI's gpt-4o-mini-transcribe (batch, $0.18 an hour, an estimate), OpenAI's gpt-4o-transcribe (batch, $0.36 an hour, an estimate), OpenAI's gpt-4o-transcribe-diarize (batch, $0.36 an hour, an estimate) and OpenAI's gpt-live-transcribe (streaming, $1.02 an hour).
Every model on each side
Google Speech-to-Text
| Model | Audio | Per minute | Per hour |
|---|---|---|---|
| V2 dynamic batch | batch | $0.003 | $0.18 |
| V2 standard | batch | $0.016 | $0.96 |
| V1 with data logging | batch | $0.016 | $0.96 |
| V1 without data logging | batch | $0.024 | $1.44 |
| V2 standard | streaming | $0.016 | $0.96 |
| V1 with data logging | streaming | $0.016 | $0.96 |
| V1 without data logging | streaming | $0.024 | $1.44 |
Whisper API
| Model | Audio | Per minute | Per hour |
|---|---|---|---|
| Whisper (whisper-1) | batch | $0.006 | $0.36 |
| gpt-realtime-whisper | streaming | $0.017 | $1.02 |
Full details: Google Speech-to-Text pricing and Whisper API pricing. Compare every vendor in the speech-to-text cost calculator, or see the cheapest speech-to-text API.
Prices on this page were checked against the official pricing pages on .