OpenClaw 4.24 Brings Voice Call Support, Faster DeepSeek Models, and Smarter Browser Automation

OpenClaw’s 4.24 release adds full voice call capability for AI agents, integrates DeepSeek V4 Flash and Pro models with a 40% inference speed boost, and enhances browser automation with coordinate clicking and error recovery, while also improving Telegram/Slack handling, multi‑channel stability, and TTS naturalness.

AI Engineering
AI Engineering
AI Engineering
OpenClaw 4.24 Brings Voice Call Support, Faster DeepSeek Models, and Smarter Browser Automation

Version 2026.4.24 Overview

Three core upgrades were introduced: voice interaction, AI model performance, and browser automation.

Voice interaction expansion

Complete voice‑call capability was added, enabling AI agents to answer telephone calls. A developer test in a customer‑service scenario reported that the agents handled roughly 80 % of routine inquiries.

AI model upgrade

DeepSeek V4 Flash and DeepSeek V4 Pro were integrated. Benchmarks show a 40 % increase in inference speed on complex tasks compared with the prior version, and automated tests demonstrate noticeably better context‑understanding.

Browser automation enhancement

A coordinate‑click feature was introduced together with an improved error‑recovery mechanism. Real‑world tests indicate that when dynamic web‑element location fails, the system can backtrack to stored coordinates and automatically correct the operation.

In an e‑commerce price‑monitoring workflow, the successful‑capture rate rose from 72 % to 89 % after applying the new automation.

Additional improvements

Optimized Telegram and Slack message handling

Stability improvements for the Multi‑Channel Protocol (MCP)

Naturalness enhancements for text‑to‑speech (TTS)

Release notes: https://github.com/openclaw/openclaw/releases/tag/v2026.4.24

PerformanceDeepSeekAI Modelsbrowser automationRPAVoice CallOpenClaw
AI Engineering
Written by

AI Engineering

Focused on cutting‑edge product and technology information and practical experience sharing in the AI field (large models, MLOps/LLMOps, AI application development, AI infrastructure).

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.