Chinese and Japanese speech with expressive delivery.
What it does
Generates Chinese and Japanese speech audio with natural-language control over emotion and delivery.
When to use it
Use for emotion-controlled speech, batch voice lines, migration from step-tts-2, or cloned voices.
How to use it
Give it speech text or a batch of voice lines; it saves generated audio to the specified output location.
Uses
Good to know
- cannot be undone: StepFun; ${CLAUDE_PLUGIN_DATA}/config.json
Latest review
What you need · 4
The bundled synthesis script runs with Python 3; no minimum minor version is stated.
Reads the preferred API key from the environment; it must be a Normal key, not a Plan key.
Access · 3
This skill
StepFun
Write
Sends text for paid speech synthesis (irreversible)
${CLAUDE_PLUGIN_DATA}/config.json
Write
Stores your API key locally (irreversible)