Add Gemini text-to-speech support

## What changed OpenClaw added Gemini text-to-speech support to its bundled Google plugin on 18 May 2026. The update lets users pick from Gemini voices and output audio as WAV or PCM files. Automated setup guidance appears in the CLI during configuration.

The change ships as a free update for all self-hosted installs. No new pricing tier is required.

## Why it matters Voice output turns OpenClaw from a text-only responder into an agent that can deliver briefings or alerts as spoken audio inside the same messaging apps users already check. This reduces context switching for Vibe Builders who run the agent on WhatsApp or Telegram.

The move pressures closed cloud agents to match multimodal output quickly. It also bets that local control over voice generation will matter more than raw model quality for daily personal-assistant tasks.

## How to use it Pull the latest OpenClaw release through the existing CLI command. Run the Google plugin setup again and select Gemini as the TTS provider when prompted. Choose a voice name and set the output format to WAV or PCM in the YAML file.

Restart the agent. Test by sending a message that triggers a spoken reply. The feature works on any plan that already connects to Google models.

## Watch for Confirm the bet if users report reliable voice check-ins without extra token spend. Watch for quality drops or sudden API rate limits that break scheduled audio briefings. Expect a follow-up integration with at least one non-Google TTS option within the next quarter.