OpenClaw v2026.4.25: In one go, added six TTS providers for voice replies; plugin startup no longer does a full scan of everything

AIMPACT update, April 27 (UTC+8). According to Beating monitoring by user study, open-source personal AI assistant OpenClaw released v2026.4.25. The two biggest changes are: voice replies have been upgraded from basic functionality to a full TTS platform, and the plugin system has moved from whole-disk scanning to cold, persistent registry indexing.

For voice replies, new /tts latest lets you read the latest reply; /tts chat on|off|default enables/disables automatic voice in the current session. A new TTS persona (role-based voice) feature is added, supporting overriding global voice settings both per agent and per account. Providers have also been expanded by six at once: Azure Speech, Xiaomi MiMo, local CLI TTS, Inworld, Volcano engine Seed Speech, and ElevenLabs v3. Voice message output on channels such as WhatsApp and Feishu has been adapted accordingly.

This release also includes an architecture-level adjustment to the plugin system. Previously, each startup required scanning all plugin manifest files to discover providers and capabilities. Now, installation metadata, capability querying, and provider discovery all go through a cold, persistent registry (a pre-indexed read-only snapshot). \openclaw plugins list\ reads the snapshot by default and no longer triggers runtime module loading; \openclaw doctor --fix\ can refresh the index on demand. The direct effect is that CLI commands like models list --all --provider run significantly faster in environments with many plugins.

Other updates: OpenTelemetry observability has been extended to model calls, token usage, tool loops, exec processes, context assembly, and memory pressure, with new Prometheus scraping routes and GenAI semantic-spec metrics added. Browser automation adds iframe-aware role snapshots, CDP readiness timeout tuning, and browser doctor --deep deep diagnostics. Control UI now supports PWA installation and Web Push notifications. For first launch, a fully interactive TUI onboarding guide (Crestodian) and a context mode selector have been added. More than 100 bug fixes cover Windows/macOS/Linux/Docker installation, WhatsApp linked device keep-alive, session resets, log rotation, and device pairing security, among others. (Source: BlockBeats)