Add Google's Gemini speech-generation API as 8th TTS backend.
Returns base64-encoded signed 16-bit PCM at 24 kHz mono, wrapped
in WAV natively via stdlib wave module. Optional ffmpeg conversion
to mp3/ogg for Telegram voice bubbles.
Supports GEMINI_API_KEY and GOOGLE_API_KEY (fallback), 30 prebuilt
voices, configurable model (flash/pro).
Cherry-picked from #10922 by @zhonghui5207. Fixes#10918.