Official documentation
Groq speech-to-text documentation: Whisper models and cost per hour
Groq, GroqCloud developer documentation, 2026
Read the originalRead on October 19, 2026
- What it is
- Groq's speech-to-text documentation for its hosted Whisper models. Its model table gives a cost per hour of audio for whisper-large-v3 and whisper-large-v3-turbo, next to language support, speed factor and word error rate. It also states the billing minimum per request.
- How much weight it carries
- The provider's own developer documentation, so it is the authority on Groq's listed Whisper prices. It gives one hourly figure per model with no volume tiers, and it does not say when the figures were last changed. Re-check before budgeting.
Facts taken from this source
- Groq's speech-to-text documentation lists whisper-large-v3 at a cost of $0.111 per hour of audio.
“Model Cost Per Hour Language Support Transcription Support Translation Support Real-time Speed Factor Word Error Rate whisper-large-v3 $0.111” (Model table, Cost Per Hour column)
- Groq's speech-to-text documentation lists whisper-large-v3-turbo at a cost of $0.04 per hour of audio.
“whisper-large-v3-turbo $0.04 Multilingual Yes No 216 12%” (Model table, Cost Per Hour column)