zai▌

High-quality text-to-speech audio generation using GLM-TTS with customizable voices and playback parameters. \n \n Converts text or file content to WAV audio via the uvx zai-tts command with configurable output paths \n Supports three built-in system voices (Lila, Chloe, Ethan) plus custom cloned voices created on audio.z.ai \n Adjustable speed (1.5x, etc.) and volume (2x, etc.) parameters for fine-tuned audio output \n Requires environment variables ZAI_AUDIO_USERID and ZAI_AUDIO_TOKEN obtained