doubao-tts
v1.0.2使用豆包（火山引擎）语音合成大模型 API 将文本转换为语音音频文件。支持声音复刻音色（S_ 开头的音色ID）和官方预置音色。当用户要求"语音合成"、"文字转语音"、"TTS"、"朗读文本"、"生成语音"、"用我的声音读"、"豆包语音"、"声音复刻合成"等相关请求时，务必使用此 skill。即使用户只是说"帮我把...
⭐ 1· 327·2 current·2 all-time
byJianjun@jianjun156
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill name/description match the included script and SKILL.md: it calls Volcengine (Doubao) TTS to convert text to audio and supports cloned and preset voices. One minor inconsistency: the package registry metadata at the top of the report listed 'Required env vars: none', but the SKILL.md and scripts clearly require DOUBAO_APP_ID and DOUBAO_ACCESS_KEY (and optionally DOUBAO_SPEAKER). This is an administrative/metadata mismatch, not a functionality mismatch.
Instruction Scope
SKILL.md instructs the agent to collect text, optional voice parameters, require Doubao credentials, then run the included Python script which sends the text to the official streaming TTS API and writes an audio file to a user-specified path. The instructions do not request unrelated files, other credentials, or exfiltrate data to unexpected endpoints.
Install Mechanism
There is no automated install spec (instruction-only). The README suggests installing the well-known 'requests' pip package; the script itself checks for requests and exits with a clear error if missing. No downloads from untrusted URLs or archive extraction are present.
Credentials
The script requires DOUBAO_APP_ID and DOUBAO_ACCESS_KEY which are appropriate and proportionate for calling the Doubao/Volcengine TTS API; an optional DOUBAO_SPEAKER is reasonable. Note again the registry metadata omission of these environment variables — the runtime docs and script do expect them.
Persistence & Privilege
The skill is not always-enabled and is user-invocable by default. It does not request persistent system privileges, modify other skills, or alter system-wide agent settings. It only creates the specified output audio file.
Assessment
This skill is internally coherent for its stated Doubao/火山引擎 TTS purpose. Before installing: 1) Confirm you are comfortable providing DOUBAO_APP_ID and DOUBAO_ACCESS_KEY (these are sent in requests to https://openspeech.bytedance.com). Keep those keys secret and do not reuse unrelated cloud secrets. 2) Be aware that any text you send (and any voice-clone ID you use) is transmitted to Volcengine's service — avoid sending sensitive PII if you have privacy concerns. 3) The registry metadata in the package listing omitted the required env vars; rely on SKILL.md and the script which do require the keys. 4) Ensure the execution environment has Python 3 and the requests package installed, and that you trust the upstream provider. If you need higher assurance, audit network traffic or run the script in an isolated environment before enabling agent-level invocation.Like a lobster shell, security has layers — review code before you run it.
latestvk973kr66vjafmv5g7btwxaesen83fj06
License
MIT-0
Free to use, modify, and redistribute. No attribution required.