Generate speech audio from text using Gemini TTS.

Rotates across all configured API keys and falls back between models. Gemini TTS voices are multilingual — any voice speaks the language of the input text automatically.

Args: text: The text content to vocalize. voice_name: Gemini voice (use list_voices to browse). Default: Puck. style_instruction: Optional speaking-style hint prepended to text, e.g. "speak softly", "cheerfully", "in a calm tone". pitch_factor: Pitch adjustment. 1.0 = no change, >1 = higher, <1 = lower. model: Model override. Default: gemini-3.1-flash-tts-preview, falls back to gemini-2.5-flash-preview-tts. output_path: Optional custom output path for the WAV file.

Returns: Absolute path to the generated WAV file, or error description.

List all Gemini TTS voices with gender, tone, and description.

Optionally filter by gender and/or tone. Gemini TTS voices are multilingual — any voice speaks the language of the input text.

Args: filter_gender: Filter by "male", "female" (case-insensitive). filter_tone: Filter by tone name, e.g. "Soft", "Bright", "Firm", "Warm", "Upbeat", "Clear", "Smooth", "Informative", "Easy-going", etc. (case-insensitive).

Returns: A formatted table of matching voices.

List Gemini TTS voices filtered by gender.

Args: gender: "male" or "female" (case-insensitive).

Returns: A formatted table of matching voices.

Reload API keys from ~/.gemini-tts-mcp/keys.json or env vars.

Check how many API keys are currently configured.