Humanlike AIThe model index

Side by side

Whisper v3 Turbo on Groq vs Gemini 3.5 Transcribe

Up to 4 models, normalised onto the same cost basis and scored through the lens you pick.

Groq logo
Whisper v3 Turbo on Groq
Groq
Google logo
Gemini 3.5 Transcribe
Google
Cost of talking
Per minuteNot conversationalNot conversational
Per hour——
30-min interview——
List pricePlan-basedEstimatePlan-basedEstimate
Recruitment fit
Overall62/10089/100
VerdictFine for internal notes; not what you want under an interview a hiring decision rests on.The pick for panel interviews and any non-English hiring — speaker attribution and Greek accuracy are both unmatched here.
Best for
Internal recruiter notesQuick voice memos
Panel interviewsMultilingual hiringEvidence-linked interview notes
Watch out for
  • Slowest tail latency of the streaming options we measured
  • No speaker attribution
  • Live and Recorded are different model codes — you cannot swap one for the other
  • Requires a billed key; the free tier 429s under sustained use
Capabilities
Modalitiesaudioaudio
Context window——
VariantsTurboLive, Recorded
On HumanLikeCoworkerCoworker, Clippy
HumanLike evals
Text still arriving after speaker stops (EN)1197 msOur eval666 msOur eval
Word error rate (English)—0.06Our eval
Word error rate (Greek)—0.03Our eval

Cost per hour assumes 150 wpm and a 40% AI speaking share. Hover a figure for its full derivation.