Fact · Transcription
0.111US dollars per hour of audio
Groq's speech-to-text documentation lists whisper-large-v3 at a cost of $0.111 per hour of audio.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“Model Cost Per Hour Language Support Transcription Support Translation Support Real-time Speed Factor Word Error Rate whisper-large-v3 $0.111”
Groq speech-to-text documentation: Whisper models and cost per hour, Groq, GroqCloud developer documentation, 2026, Model table, Cost Per Hour column.
Open the original- What it measures
- The model table compares Groq's hosted Whisper models. The cost column is headed Cost Per Hour, and this row is the figure for whisper-large-v3, the multilingual model that also translates.
- What it does not show
- A list price read on 2026-10-19. The table gives no volume tiers or discounts. Each request is billed a minimum of 10 seconds, according to the same page.
In the data
A row of Speech-to-Text API Pricing: Cost per Hour of Audio, as Groq whisper-large-v3: 0.11 US dollars per hour of audio.
- Provider
- Groq
- Product
- whisper-large-v3
- Mode
- Batch (recorded audio)
- As of
- 2026-10
Source
Used to calculate
- In the speech-to-text and transcription prices dataset, the 22 published figures for “Batch (recorded audio)” have a median of 0.21 US dollars per hour of audio, ranging from 0.04 to 6.
- The speech-to-text and transcription prices dataset holds 34 data points, each a published figure traced to its source.
- The speech-to-text and transcription prices dataset draws on 15 distinct sources.