Inference APIs
Compare/Speech-to-text

Whisper Large v3 Turbo vs Deepgram Nova-3

Whisper Large v3 Turbo is an open-weight speech-to-text model you can call on this endpoint; Deepgram Nova-3 is a closed model from Deepgram. Below: what each costs for three realistic workloads, the limits that apply, and when to choose which.

Deepgram figures are public list prices and documented limits, checked 2026-09-16 against the provider page. Inference APIs prices are read live from the price list.

Short answer
  • Cost: Whisper Large v3 Turbo is cheaper in all three workloads, by 87%.
  • Limits: Deepgram: Concurrency limits by plan. Here: no per-minute or per-day caps.

Side by side

Whisper Large v3 TurboDeepgram Nova-3
Served byInference APIsDeepgram
Model authorOpenAIDeepgram
Model idopenai/whisper-large-v3-turbonova-3
Price$0.001 / audio minute$0.0077 / audio minute
CapabilitiesSpeech to text, 100 languages, Word timestamps, Speaker diarization, SRT / VTTSpeech to text, Streaming, Diarization, Keyterms
WeightsOpenClosed
StatusAvailableAvailable
LimitsNo per-minute or per-day request or token caps; usage draws on a prepaid balanceConcurrency limits by plan.

What three workloads cost

List prices applied to the same work. The cheaper side of each row is in bold.

WorkloadWhisper Large v3 TurboDeepgram Nova-3Difference
1 hour of audio$0.06$0.4687%
100 hours of audio$6.00$46.2087%
1,000 hours of audio$60.00$46287%

Whisper Large v3 Turbo is cheaper in all three workloads, by 87%.

When to choose which

Choose Whisper Large v3 Turbo if
  • Cost is the deciding factor; it is cheaper in every workload above
  • You want open weights: the same model can be moved to another host or self-hosted later
  • Long files and batch jobs where speed matters more than the last bit of accuracy
  • Code written for Groq's whisper-large-v3-turbo id
  • An hour of audio in about 17 seconds for $0.06
  • You only transcribe recorded files and want the lowest per-minute price
Choose Deepgram Nova-3 if
  • You need real-time streaming transcription
  • You need speaker diarization or keyterm prompting

FAQ

Which is cheaper, Whisper Large v3 Turbo or Deepgram Nova-3?

Whisper Large v3 Turbo is cheaper in all three workloads, by 87%. The table above uses list prices: Whisper Large v3 Turbo $0.001 / audio minute; Deepgram Nova-3 $0.0077 / audio minute.

What limits apply to Deepgram Nova-3?

Concurrency limits by plan. On Inference APIs there are no per-minute or per-day request or token caps; usage draws on a prepaid balance.

Spotted a price or limit that has changed? Tell us and we will re-check the provider page.