stepfun-tts

Generate Chinese / Japanese speech with StepFun's stepaudio-2.5-tts — Contextual TTS that replaces step-tts-2's `voice_label` with natural-language `instruction` (≤200 chars) plus inline `()` parentheses for句内 prosody. Use when the user wants emotional / prosody control over voice synthesis (whisper

By daymade · 534 installs

npx skills add daymade/claude-code-skills --skill stepfun-tts

Source repository · Upstream listing