Sapi Tts
v1.1.0Windows SAPI5 text-to-speech with Neural voices. Lightweight alternative to GPU-heavy TTS - zero GPU usage, instant generation. Auto-detects best available voice for your language. Works on Windows 10/11.
⭐ 1· 2.4k·6 current·6 all-time
byPocus@korddie
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description claim Windows SAPI5 TTS; the SKILL.md supplies a PowerShell script that uses System.Speech and PresentationCore to list voices, pick a voice, synthesize to WAV, and optionally play — these are exactly the capabilities needed for on‑device SAPI5 TTS. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
Instructions stay within TTS scope (enumerate installed voices, select best match, write WAV, optionally play). The script writes output files under $env:USERPROFILE\.openclaw\workspace\tts (creates that directory if missing) — benign for a local TTS tool but worth noting. Also the SKILL.md and script target Windows 10/11, whereas registry metadata lists no OS restriction (minor metadata mismatch).
Install Mechanism
No install spec and no code files beyond SKILL.md; user is asked to save the provided PowerShell script — lowest-risk installation model (nothing is downloaded or executed automatically by the registry).
Credentials
No environment variables, credentials, or external config paths are required. The script references only $env:USERPROFILE to build a local output path, which is appropriate for generating files in the user's workspace.
Persistence & Privilege
Skill is not always-enabled, does not request elevated privileges, does not modify other skills or system configurations beyond creating its own output directory and files. Agent autonomous invocation remains default but is not combined with broad access here.
Assessment
This is an instruction-only Windows PowerShell TTS script that appears coherent and low risk. Before installing: (1) review the tts.ps1 contents (the SKILL.md contains the full script) to confirm you’re comfortable with it writing WAV files to $USERPROFILE\.openclaw\workspace\tts; (2) run it only on Windows 10/11 (it uses .NET System.Speech and PresentationCore); (3) if you prefer not to keep generated files, specify a custom -Output path or periodically clean the folder; (4) ensure your PowerShell execution policy/privileges are appropriate (you may need to unblock the script), and (5) if you have any security policy forbidding running third‑party scripts, treat this like any other user-provided script and run it in a controlled environment or sandbox first.Like a lobster shell, security has layers — review code before you run it.
latestvk979rg133qbvv90021t6m6j2vn80nfbk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.