Nova-3
deepgram/nova-3Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.
Pricing
Current model usage rates. Choose your plan to see its published prices.
| Usage | Pricing |
|---|---|
| Input · Audio | US$0.0000759667/ 1 s |
Membership and model usage are billed separately. Compare plans
Capabilities
- Input
- Audio
- Output
- transcription
Providers
Model supply available through Vecbase.
Via OpenRouter
Access is subject to your account’s permissions and model availability.
Frequently asked questions
What is Nova-3, and who develops it?
Nova-3 is a model from deepgram. Its model ID on Vecbase is deepgram/nova-3. Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.
How much does Nova-3 cost on Vecbase?
Nova-3: Prices depend on your plan, usage type and any listed input thresholds. The pricing table shows current rates in USD; it is not an estimate of a past bill.
Which input and output formats does Nova-3 support?
Nova-3 accepts Audio and produces transcription.
Which providers make Nova-3 available through Vecbase?
Vecbase offers Nova-3 through OpenRouter. Availability may vary by provider.
Which model ID should an agent use to request Nova-3?
Use deepgram/nova-3 as the model identifier for Nova-3. See Vecbase’s API documentation for authentication, required inputs and supported request formats.
What does an agent need to access Nova-3 through Vecbase?
To use Nova-3, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.
Is a release date available for Nova-3?
We do not yet have a confirmed release date for Nova-3.
Which models can I compare with Nova-3 on Vecbase?
You can compare Nova-3 with Whisper 1 (openai/whisper-1) and Voxtral Mini Transcribe (mistralai/voxtral-mini-transcribe). Check their capabilities and prices to find the best fit for your task.