LangSmith adds tracing for four voice-agent stacks, including OpenAI Realtime and Gemini Live
hwchase17 · x · 2026-07-22
LangChain says LangSmith tracing now supports four voice-agent stacks: Pipecat, LiveKit, OpenAI Realtime, and Gemini Live via Google ADK.
The company frames the launch as a way to make production voice agents less of a black box. The post also argues that teams building text agents with LangChain can reuse much of that observability knowledge when moving to voice.
The integrations cover speech-to-speech APIs from OpenAI and Google, plus orchestration frameworks used for voice AI production workflows.
Related event: LangSmith Launches Native Tracing for Voice Agents Across Four Frameworks(6 posts)→
More from coding & agent
- TRL adds Score Centering, a simple fix for RLHF training instability — lvwerra · 2026-10-27
- Precompute golden answers and match at runtime for exact wording control — colinmcnamara · 2026-10-27
- Dev argues there's still alpha in working with your coding agent interactively — alex_frantic · 2026-10-27
- Researchers launch AMA on patterns for safer AI agents used by citizen developers — Loose_Rip359 · 2026-10-27
- Gradio Adds In-Chat Human-in-the-Loop So ML Intern Pauses Before Training — Gradio · 2026-10-27
- Building Halo Infinite Forge maps with local LLMs, DCjson and Blender MCP — swagonflyyyy · 2026-10-27