Built for voice agents that can't wait 600ms

Deepgram: Aura-2

deepgram/aura-2
Text to speechactive

Deepgram's enterprise-grade text-to-speech model with an expanded voice catalog and context-aware delivery, targeting sub-200ms latency at high concurrency. Deepgram's full Aura-2 catalog is multilingual; this seed covers the English (-en) voices.

ProviderSlugPriceLatencyUptime