概要
The Text-to-Speech skill for telclaude enables Claude to generate spoken responses and audio files directly within Telegram. It leverages OpenAI's advanced TTS models to provide realistic voices, supporting both standard audio files and native Telegram voice messages with waveform displays. Whether replying to an incoming voice note in the same language or narrating long-form content, this skill allows for seamless auditory interaction with AI, offering customizable voices, speeds, and quality levels to suit various accessibility and productivity needs.
