Google publishes guide on non-blocking tools for ADK voice agents
10/21/2026 — 10/21, 23:27·2 sources (all)·2 reports (all)
Key takeaways
- Google Developers Blog published a step-by-step guide showing how to build non-blocking and streaming tool calls in Python with the open-sou…
Google Developers Blog published a step-by-step guide showing how to build non-blocking and streaming tool calls in Python with the open-source Agent Development Kit and gemini-3.8-live, keeping a voice agent talking during long-running queries. In a benchmark sales-report flow, first-word latency dropped from 14.4 seconds to 1.2 seconds, and developers can use WHEN_IDLE, INTERRUPT and SILENT scheduling policies to control result delivery.
Latest turnGoogle has released Gemini 3.8 Flash, a multimodal foundation model engineered for long-horizon software engineering and multi-step reasoning. The model features a 1-million-token context window, adjustable reasoning effort levels, and an introductory price of $0.75 per million input tokens.
Related AI tools
- Heat index
- 152
- All sources
- 2
- All reports
- 2
- First seen
- 20 hours ago
Reports on this story headlines open the original
Google has released Gemini 3.8 Flash, a multimodal foundation model engineered for long-horizon software engineering and multi-step reasoning. The model features a 1-million-token context window, adjustable reasoning effort levels, and an introductory price of $0.75 per million input tokens.
DEV Community · AIAI score 72Google's developer blog published a step-by-step guide on using the open-source Agent Development Kit with gemini-3.8-live to build voice agents with non-blocking and streaming tools in Python. In Google's benchmarked sales-report workflow, switching from a blocking to a streaming tool cut time to first words from 14.4 seconds to 1.2 seconds. Response scheduling options such as WHEN_IDLE, INTERRUPT and SILENT control when tool results are spoken.
Google Developers BlogFirst-partyAI score 53
Other stories people are talking about
- Heat index 295Mistral releases Voxtral 3 voice agent SDK for real-time speech5 sources
- Heat index 96NewGoogle Brings Conversational Gemini Navigation to Apple CarPlay via Google Maps1 sources
- Heat index 192NewGoogle Chrome Enhanced Protection Adds Scam CLI Detection and Gemini Server-Side Analysis2 sources
- Heat index 99NewUsers Can Free Up Disk Space by Clearing Local Gemini Nano Weights in Chrome1 sources
- Heat index 966RisingDeepSeek open-sources DeepInfer large-scale inference framework16 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion