vaaya / catalog / deepgram nova-3
Deepgram Nova-3 for AI agents
Deepgram's speech model for fast, accurate speech-to-text with speaker labels and timestamps. Called through Vaaya, billed per call — no Deepgram account.
1¢ per audio minute
Model by Deepgram. Called through Vaaya — no Deepgram account or API key.
What it's for
Fast, accurate speech-to-text with speaker labels and timestamps.
Built by Deepgram. Runs on your Vaaya balance — no Deepgram account or API key.
Request it by name, or describe the audio and Vaaya routes to a fitting model.
Returns an audio URL.
How to ask your agent
Connect Vaaya, then just say it in plain language. For example:
❯Use Vaaya to transcribe this interview and label who said what.
❯Use Vaaya to run this on Deepgram Nova-3.
What you get back
{
"audio": { "url": "https://…/output.mp3" },
"model": "deepgram/transcribe"
}
Pricing
1¢ per minute of audio transcribed. Billed per call in cents, capped by your max, every call on the ledger. Failed calls are not billed.
Give your agents this.
Connect Vaaya once, then describe the outcome. It picks the right tool, runs it, and pays per call.
npx @vaaya/mcp install