
Whisper v3 Turbo on Groq
audio model · Available
GroqThe fast tier, cheapest path to a good-enough transcript.
Fit and price
Recruitment fit
62
Per hour
n/a
Per minute
n/a
30-min interview
n/a
About
Groq’s Whisper v3 Turbo is the "Fast" tier in Coworker. It is not the most accurate model in our harness and its tail latency (1197ms EN / 1273ms EL) is the slowest of the streaming options we measured, but it is cheap and dependable for everyday notes.
- Very low cost
- Wide language coverage
- Open-weights lineage
Strengths and watch-outs
Strengths
- Cheap enough to leave on
- Broad language coverage
Watch out for
- Slowest tail latency
- No speaker attribution
Best for Internal recruiter notes · Quick voice memos
The numbers
HumanLike evals
- Text still arriving after speaker stops (EN)
- 1197 msOur eval