SKILLEMALL.ai
GitHub ↗ RU Sign in

BD xiaomi-any2speech

声音世界模型（Speech World Model）：不只是 TTS，而是理解场景、角色、情绪并自主规划表达的语音大模型。 原生支持长文+多人、中英双语，也支持上传参考音频进行音色克隆（Voice Prompt / voice cloning），内置高能创作模板，将任意内容转为播客/有声书/相声/Rap/广播剧等，单次最长 ~10 分钟，输出 WAV。 涵盖单人TTS、VoiceDesigner音色定制、参考音频克隆、多人人物对话合成、长文有声化、Instruct TTS 的超集。 A Speech World Model: beyond TTS — understands scenes, characters, and emotions to autonomously plan expressive speech. Native long-form & multi-speaker synthesis in Chinese/English, and supports reference-audio voice cloning (Voice Prompt), up to ~10 min per pass. 触发意图：用我的声音/用这个音色/参考这段录音/克隆声音/模仿声音、做成播客/相声/辩论/有声书/Rap/新闻/脱口秀/电台/课程/广播剧/评书/讲故事、朗读/念出来/转语音/TTS/生成音频/做个语音版/配音、变成能听的/用XX腔念、发语音/做成XX发给我、用模板/选模板/有什么模板。 English: make a podcast/audiobook/debate/rap/news/stand-up/story/radio drama, read aloud/TTS/generate audio/voice over/narrate/dub/mimic voice/clone voice/use my voice/use this voice sample, make it listenable, send as voice.

ClawHub Agent Skills author: Di Wu v1.0.7 MIT-0 2 files body ≈ 2 440 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorAI and agentsInfrastructureMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
83
Quality 40%
81
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Exfiltration net-credential-use SKILL.md:89
      Credential used in a network call (verify the destination is the intended service)
      STATUS=$(curl -s -H "Authorization: Bearer $API_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:98
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $API_KEY" \
    • medium Exfiltration net-credential-use SKILL.md:193
      Credential used in a network call (verify the destination is the intended service)
      curl -s -H "Authorization: Bearer $API_KEY" "$BASE/v1/audio/vp/templates" \
    • low Exfiltration net-credential-use SKILL.md:185
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      > 降噪预览（不合成，仅试听降噪效果）：`curl -X POST "$BASE/v1/audio/vp/denoise" -H "Authorization: Bearer $API_KEY" -F "voice_file=@ref.webm" --output denoised.wav`。当前返回标准 WAV，采样率为 48kHz。
      quoted
    • low Exfiltration net-credential-use SKILL.md:245
      Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
      [ -z "$FEISHU_TENANT_TOKEN" ] && FEISHU_TENANT_TOKEN=$(curl -s -X POST \
      quoted

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 41/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (xiaomi-any2speech) differs from the folder (xiaomi-any2speech-beyondtts)
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 10 steps
    • 100Execution cost. Instruction body is 2440 tokens
    • 100Running it twice. No mutating operations

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 880: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 10 items
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

    External checks

    ClawHub: clean
    This skill is a disclosed Xiaomi text-to-speech and voice-cloning workflow, but users should understand that supplied text, files, URLs, and voice samples may be uploaded to external services.
    LLM: benign (high) · VirusTotal: · 29 May 2026