Baseten releases Voice Agent Stack and Realtime Voice
Understand this story
Baseten releases the Voice Agent Stack and the Realtime Voice voice agent API built on it, for teams to build, deploy, and manage voice agent systems. Both products are currently in private preview and require applying via waitlist. Baseten says calls handed off to larger inference models are billed per token, the same as standard LLM endpoints.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Baseten BlogIntroducing the Baseten Voice Agent Stack: own and optimize voice agents end-to-end
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.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 17 02:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.