Summary
OpenClaw's 2026.4.25 release overhauled voice replies with chat-scoped auto-TTS controls, persona support, per-agent and per-account overrides, and new provider coverage including Azure Speech, Xiaomi, Local CLI, Inworld, Volcengine, and ElevenLabs v3. The change expands OpenClaw from basic voice output into a more configurable voice layer for multi-agent deployments.
What changed
OpenClaw shipped a broad TTS upgrade that adds richer controls and expands provider coverage across multiple commercial and local speech engines.
Why it matters
Voice output is becoming part of the agent product surface, especially for assistants embedded in messaging, support, and mobile flows. OpenClaw is using TTS breadth and configurability to make its agent stack more adaptable across accounts, personas, and deployment environments.
Evidence excerpt
The 2026.4.25 release highlights a full TTS upgrade with /tts latest, chat-scoped auto-TTS controls, personas, per-agent and per-account overrides, and new Azure Speech, Xiaomi, Local CLI, Inworld, Volcengine, and ElevenLabs v3 coverage.