Azure Speech to Text vs Whisper API on price
Azure 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, Azure AI Speech's Batch transcription costs $0.18 an hour against $0.36 for OpenAI's Whisper (whisper-1), 50% less; for live audio, Azure AI Speech's Real-time transcription costs $1 an hour against $1.02 for OpenAI's gpt-realtime-whisper, 2% 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 | Azure Speech to Text | Whisper API |
|---|---|---|
| 10 hours | $1.80 ($0.18/h) Batch transcription | $3.60 ($0.36/h) Whisper (whisper-1) |
| 100 hours | $18 ($0.18/h) Batch transcription | $36 ($0.36/h) Whisper (whisper-1) |
| 1,000 hours | $180 ($0.18/h) Batch transcription | $360 ($0.36/h) Whisper (whisper-1) |
| 10,000 hours | $1,800 ($0.18/h) Batch transcription | $3,600 ($0.36/h) Whisper (whisper-1) |
Live audio (streaming)
| Audio a month | Azure Speech to Text | Whisper API |
|---|---|---|
| 10 hours | $10 ($1/h) Real-time transcription | $10.20 ($1.02/h) gpt-realtime-whisper |
| 100 hours | $100 ($1/h) Real-time transcription | $102 ($1.02/h) gpt-realtime-whisper |
| 1,000 hours | $1,000 ($1/h) Real-time transcription | $1,020 ($1.02/h) gpt-realtime-whisper |
| 10,000 hours | $10,000 ($1/h) Real-time transcription | $10,200 ($1.02/h) gpt-realtime-whisper |
What else changes the bill
| On the bill | Azure Speech to Text | Whisper API |
|---|---|---|
| Free tier or credit | A separate free tier (F0) gives 5 audio hours a month of real-time transcription; batch isn't supported on it. | No free allowance or credit is listed on OpenAI's pricing page. |
| Billing | Billed per second of audio sent. | OpenAI's pricing page doesn't say how partial minutes are counted. |
| Speaker labels, recorded audio | Included. | Through the separate gpt-4o-transcribe-diarize model, at the same estimated $0.006 a minute as gpt-4o-transcribe. |
| Speaker labels, live audio | +$0.30 an hour. | 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).
Azure Speech to Text or Whisper API: quick answers
Is Azure Speech to Text cheaper than Whisper API?
For recorded audio, Azure Speech to Text is cheaper at every volume from 1 minute to 10,000 hours a month. At 1,000 hours a month that's $180 a month apart, $2,160 a year ($180 on Azure Speech to Text's Batch transcription against $360 on Whisper API's Whisper (whisper-1)). For live audio, Azure Speech to Text is cheaper at every volume from 1 minute to 10,000 hours a month. At 1,000 hours a month that's $20 a month apart, $240 a year ($1,000 on Azure Speech to Text's Real-time transcription against $1,020 on Whisper API's gpt-realtime-whisper). Regular pay-as-you-go prices, each side's cheapest model.
How much more does live transcription cost than recorded on Azure Speech to Text and Whisper API?
On Azure Speech to Text, live audio costs 456% more than recorded, $1 an hour on Real-time transcription against $0.18 on Batch transcription; on Whisper API, live audio costs 183% more than recorded, $1.02 an hour on gpt-realtime-whisper against $0.36 on Whisper (whisper-1). Each side's cheapest model for each kind of audio at 100 hours a month, at its list price.
Do Azure Speech to Text and Whisper API have a free tier or free credit?
Azure Speech to Text: A separate free tier (F0) gives 5 audio hours a month of real-time transcription; batch isn't supported on it. Whisper API: No free allowance or credit is listed on OpenAI's pricing page.
Do Azure Speech to Text and Whisper API bill per second?
Azure Speech to Text: Azure AI Speech says “Speech to text hours are measured as the hours of audio sent to the service, billed in second increments.” Whisper API: OpenAI's pricing page doesn't say how partial minutes are counted.
What do speaker labels add on Azure Speech to Text and Whisper API?
For recorded audio: Azure Speech to Text includes them; Whisper API offers them through the separate gpt-4o-transcribe-diarize model, at the same estimated $0.006 a minute as gpt-4o-transcribe. For live audio: Azure Speech to Text charges $0.30 an hour extra; Whisper API's pricing page doesn't list them.
Do Azure Speech to Text or Whisper API give volume discounts?
Azure Speech to Text: Monthly commitment tiers for standard speech to text: $1,600 for 2,000 hours, $6,500 for 10,000 hours and $25,000 for 50,000 hours, with overage at $0.80, $0.65 and $0.50 an hour. Whisper API: no volume discount is listed on its pricing page.
Every model on each side
Azure Speech to Text
| Model | Audio | Per minute | Per hour |
|---|---|---|---|
| Batch transcription | batch | $0.003 | $0.18 |
| Fast transcription | batch | $0.006 | $0.36 |
| MAI Transcribe-1.5 | batch | $0.006 | $0.36 |
| LLM Speech | batch | $0.006 | $0.36 |
| Real-time transcription | streaming | $0.0167 | $1 |
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: Azure 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 .