Baseten Blog·· 1 days agoAI score58
Introducing the Baseten Voice Agent Stack: own and optimize voice agents end-to-end
Introducing the Baseten Voice Agent Stack: own and optimize voice agents end-to-end
AI summary
Baseten launched the Baseten Voice Agent Stack, customizable low-latency infrastructure for running production voice agents on Baseten Dedicated Inference, alongside Baseten Realtime Voice, a reference agent built on it that reports sub-second median turn latency across 32 concurrent sessions. Realtime Voice uses Baseten-optimized open-weight speech models with a Pipecat-based orchestrator, costs about $0.01 per audio minute, speaks the OpenAI Realtime protocol, and scores 93% on Full-Duplex-Bench and 73.5% on τ²-Bench Voice (self-reported). Both are in private preview with a waitlist.
Source: Baseten Blog · baseten.co