TOOL API

text_to_audio

Text to speech via Fish Audio S2/S2.1 Pro. Supports 80+ languages, cloned voice_id, and inline emotion tags like [whisper] / [excited]. Returns an audio URL. 参数: - text: 要合成的文本（必填）。可用 [whisper]、[excited]、[laughing] 控情绪 - voice_id: 音色 ID（list_voices 返回的 id）。空则用该语言默认声 - model: s2.1-pro（默认）/ s2.1-pro-free / s2-pro / s1 - format: mp3 / wav / opus / pcm - speed: 语速，默认 1.0 - latency: normal（质量）/ balanced / low