← Back to Skills Marketplace
Yummy Gen Voice
by
yummysource
· GitHub ↗
· v1.1.0
· MIT-0
164
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install yummy-gen-voice
Description
Use when the user wants to synthesise speech or text-to-speech (TTS) audio with Gemini through yummycli, including single-speaker narration, multi-speaker di...
Usage Guidance
This skill appears to do what it claims (use Gemini via the yummycli tool) and only needs GEMINI_API_KEY. Before installing or enabling it: 1) Confirm whether the skill actually installs @yummysource/yummycli (the SKILL.md contains an npm install block but the registry summary said there was no install spec). 2) Inspect the @yummysource/yummycli package (npm/GitHub) to ensure it is from a trusted publisher and review what files it writes and any network behavior. 3) Be aware the skill runs CLI commands that will create .wav files in the current working directory and may call yummycli auth status; run it in a sandbox or isolated environment if you are unsure. 4) Review the related yummy-shared skill before chaining them. If you want higher assurance, request the package source repo or a signed release before installing.
Capability Analysis
Type: OpenClaw Skill
Name: yummy-gen-voice
Version: 1.1.0
The yummy-gen-voice skill is a legitimate wrapper for text-to-speech synthesis using Google Gemini via the 'yummycli' command-line tool. The SKILL.md and _meta.json files contain standard operational instructions, voice mappings, and installation steps (@yummysource/yummycli) without any evidence of data exfiltration, malicious execution, or harmful prompt injection.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description, required binary (yummycli), and primaryEnv (GEMINI_API_KEY) are coherent with a Gemini TTS wrapper. Declared related skill (yummy-shared) and commands (yummycli gemini speak/voices) match the stated purpose.
Instruction Scope
SKILL.md instructs only about running yummycli commands, choosing models/voices, and reading the CLI JSON output. It does not ask to read unrelated files, harvest extra environment variables, or transmit data to unexpected endpoints. It does request checking auth status before running, which is reasonable.
Install Mechanism
SKILL.md includes an install block that installs the npm package @yummysource/yummycli (bins: yummycli). The registry metadata provided to you earlier said "No install spec," creating a packaging/metadata inconsistency — confirm which is authoritative. Installing an npm package is a moderate-risk action (external code will be written/executed); verify the package's provenance (npm/GitHub) before running.
Credentials
Only GEMINI_API_KEY is declared as the primary credential, which is expected for a Gemini TTS integration. No other unrelated secrets or config paths are requested.
Persistence & Privilege
Skill is not always-enabled and is user-invocable; it does not request elevated or persistent system privileges. There is no indication it modifies other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install yummy-gen-voice - After installation, invoke the skill by name or use
/yummy-gen-voice - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
- Added detailed usage instructions for synthesising speech and generating text-to-speech (TTS) audio with Google Gemini via yummycli.
- Supports single-speaker narration, multi-speaker dialogue (up to 2 speakers), and listing available voices.
- Outlines model and voice selection rules, including mapping user requests to TTS models and prebuilt voice styles.
- Documents command syntax, flag behavior, and strict execution/validation rules.
- Includes example commands and clarifies output formats and error-handling procedures.
Metadata
Frequently Asked Questions
What is Yummy Gen Voice?
Use when the user wants to synthesise speech or text-to-speech (TTS) audio with Gemini through yummycli, including single-speaker narration, multi-speaker di... It is an AI Agent Skill for Claude Code / OpenClaw, with 164 downloads so far.
How do I install Yummy Gen Voice?
Run "/install yummy-gen-voice" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Yummy Gen Voice free?
Yes, Yummy Gen Voice is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Yummy Gen Voice support?
Yummy Gen Voice is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Yummy Gen Voice?
It is built and maintained by yummysource (@yummysource); the current version is v1.1.0.
More Skills