The fastest, most accurate STT for production voice agents.
Deepgram Nova is Burki's default STT for a reason — it delivers sub-200ms transcription latency on streaming audio, the highest accuracy in independent benchmarks, and confidence-scored output Burki uses for endpointing and turn-taking.
A voice AI assistant is only useful when it can connect to the rest of your stack. The Deepgram integration helps Burki fit into the systems your team already uses for calling, transcription, reasoning, speech, routing, or customer data. That means the assistant can move from a demo into a production workflow without forcing you to replace your existing tools.
Burki keeps the integration flexible. You can run one assistant with Deepgram, pair it with other providers for a full voice pipeline, and change providers later if your cost, latency, coverage, or quality requirements change. This is especially useful for teams that need different settings per assistant, region, campaign, or customer segment.
The result is a voice agent that is easier to operate: fewer hard-coded assumptions, clearer provider boundaries, and a pricing model that separates Burki's platform fee from the third-party services you already trust.
Choose Deepgram for any production voice AI deployment where latency and accuracy matter. Switch to Azure STT if you have a strict Microsoft-only stack requirement.
# .env
DEEPGRAM_API_KEY=...
# Per-assistant config in dashboard:
# STT -> Provider: Deepgram
# Model: nova-3 (or nova-2 for cost-optimized)
# Language: multi # auto-detect, or pin to en-US, etc.For full setup, see the docs.
Burki: $0.03/min platform fee. Deepgram Nova: ~$0.0043/min for streaming on the Pay-As-You-Go plan. With BYO keys you pay Deepgram directly. Combined cost of Burki + Deepgram is dramatically lower than any platform that bundles STT.