ClawHub

Google Gemini TTS

v1.0.3

Generate spoken audio from text using Google's Gemini TTS models (default is Gemini 3.1 Flash TTS Preview, with fallback to Gemini 2.5 Flash/Pro preview TTS)...

⭐ 0· 21·0 current·0 all-time
byShubham Saboo@shubhamsaboo
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (Gemini TTS) align with required binaries (curl, jq, base64, ffmpeg) and a GEMINI_API_KEY. The script calls the Google Generative Language TTS endpoint and performs local audio conversion — all expected for a TTS wrapper.
✓
Instruction Scope
SKILL.md and the shipped script limit actions to building a TTS request, POSTing to https://generativelanguage.googleapis.com, decoding returned base64 audio, converting PCM→WAV with ffmpeg, and writing a local output file. The script checks only the declared binaries and the GEMINI_API_KEY (or alias) and does not read unrelated system files or other environment secrets.
✓
Install Mechanism
No install spec (instruction-only) and the included files are simple shell/script/text files. Nothing is downloaded or extracted at install time, so there is no high-risk installer behavior.
ℹ
Credentials
Only GEMINI_API_KEY is required (the script also accepts GOOGLE_API_KEY as an alias). This is appropriate for a Google API wrapper. Note: using GOOGLE_API_KEY as a shared env var may overlap with other tools that also read that name; prefer a dedicated GEMINI_API_KEY if you want to limit exposure.
✓
Persistence & Privilege
always is false and the skill does not attempt to persist itself or change other skills/configs. The agent-autonomy flag is default; combined with the limited scope and single API key requirement this is standard for an invocable TTS skill.
Assessment
This skill appears to do exactly what it says: call Google's Gemini TTS API and save WAV output after converting raw PCM with ffmpeg. Before installing, confirm you trust the source (owner/slug) and intend to provide a GEMINI_API_KEY: the key will be sent to https://generativelanguage.googleapis.com. Prefer setting a dedicated GEMINI_API_KEY rather than reusing a shared GOOGLE_API_KEY environment variable to reduce accidental key sharing across tools. Also review the script if you want to change output paths or retention of temporary files, and be aware API usage may incur billing on the associated Google account.

Like a lobster shell, security has layers — review code before you run it.

latestvk970c6hgn58fzfph5719bm7v0x84zc5b

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🔊 Clawdis
Binscurl, jq, base64, ffmpeg
EnvGEMINI_API_KEY
Primary envGEMINI_API_KEY

Comments