技能列表

说中文出外语语音——按住说中文，2-3秒内播放英/日/韩语音。支持场景模式、双向对话、常用句收藏。

Record experimental procedures and observations via voice commands during

根据输入法语音识别文本或润色后文本生成单张表情包图片。适用于用户想把一句话做成聊天可发送的表情包、meme 图、带字梗图或贴纸图时。支持原始语音文本和润色后文本两种输入，默认优先使用润色后文本；自动根据文本语气判断风格；默认直接生成带字图片，也支持生成无字图并同时给出配文模板；使用 doubao-seedream-4-5-251128 作为默认图片模型。

Add same-modality conversation behavior to an agent: voice in → voice out, text in → text out. Use when enabling Telegram/Feishu voice-note workflows with Edge TTS, documenting agent voice preferences, and providing gateway config snippets for inbound-only TTS auto replies.

|

Recommend the best SenseAudio voice for any scenario or emotion. Use when users ask which voice to use — e.g. "儿童故事播客用什么音色", "电商直播带货适合哪个声音", "我需要撒娇感的女声", "有没有傲娇的音色". No API key needed for recommendations; optionally generates a TTS preview sample.

Guide users through SenseAudio platform voice cloning, then generate TTS with cloned `voice_id` values. Use when users want to clone voices, manage cloned voice slots, or synthesize audio with a cloned voice.

|

vn.py 开源量化交易框架 - 支持CTA、价差、期权策略，20+券商接口，覆盖国内外市场。

Track vitamin and supplement intake with goals and reminders. Use when logging supplements, setting nutrition goals, reviewing history, or scheduling doses.

Automates Blender via Python scripts to create 3D assets, renders, and animations.

Resize, crop, convert, and optimize images using ImageMagick. Use when processing photos, converting formats (PNG/WebP), compressing size, or adding watermarks.