LangChain adds tracing for Gemini Live voice agent loops
_philschmid · x · 2026-07-23
LangChain can now trace Gemini Live speech-to-speech agent loops
If you are building real-time voice agents with Gemini Live, you can now trace the full speech-to-speech loop directly in LangChain/LangSmith.
The update adds:
- Speaker callback hooks that capture exactly the audio the user heard before an interruption.
- Live timeline visualization with user speech in blue, Gemini responses in orange, and custom tool calls such as a 1.29-second weather lookup.
- Usage metadata that separates standard text tokens from native Gemini audio tokens, so usage tracking stays accurate.
In Google ADK, you can enable it by registering LangSmithGoogleADKLivePlugin.
More from coding & agent
- Mapping Open-Source AI with Codex Agents: Mask2Former Found Lagging Behind SOTA — NielsRogge · 2026-07-23
- New tool manages fleets of agents across Claude Code, Codex and Cursor — dee_hw · 2026-07-23
- Dan Vega is prototyping Figma thumbnail concepts with Claude Code Skills — therealdanvega · 2026-07-23
- Databricks explains when to use Genie Agents, Knowledge Assistant, and a Supervisor — CautiousUse8597 · 2026-07-23
- Sentence Transformers 5.6.1 fixes a silent flash-attention regression in RoBERTa models — tomaarsen · 2026-07-23
- sentence-transformers 5.6.1 fixes Flash Attention embedding bug in XLM-R models — tomaarsen · 2026-07-23