Speech

Skill yigityildiz0/universal-ai-skill-library/skills/common/speech

531 searchable AI Agent Skills for Claude Code, OpenAI Codex, and OpenCode — EN/TR catalog, platform and risk notes, direct ZIPs, and curated bundles.

Install

npx -y skills add yigityildiz0/universal-ai-skill-library --skill speech

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate speech audio from text with an already configured local or approved text-to-speech capability, using current supported voices/models verified at.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.9 KB, 316 tokens by cl100k_base, as published. Nobody here has run it

Speech Generation

Plan

Confirm script, language, pronunciation, audience, tone, pace, pauses, file format, sample rate, channel layout, loudness target, clip boundaries, and whether disclosure of synthetic audio is required. Normalize dates, numbers, abbreviations, URLs, and domain terms without changing meaning.

Capability and consent

Use the active host's existing TTS tool, configured API, or installed local engine. Verify supported voices, formats, limits, and current model identifiers from installed/current official documentation. Do not hard-code a dated default or route to a different provider. A paid/network call, dependency install, or new credential requires authorization.

Do not imitate or clone a real person's voice without clear permission and a supported consent process. Never use synthetic speech for deception, impersonation, bypassing authentication, or undisclosed high-stakes communication.

Generate

Start with a short pronunciation/style sample before a long render. Keep chunks at natural sentence/paragraph boundaries and preserve deterministic settings when the engine supports them. Use a pronunciation glossary or supported markup rather than spelling hacks that damage captions.

Validate

Listen to or inspect every produced clip. Check exact words, names/numbers, truncation, repeated/missing phrases, clipping, silence, artifacts, loudness consistency, duration, format, and join seams. Preserve the source script and generation settings. Provide captions/transcript where useful.

Report engine/provider used, whether data left the device, voice/model configuration source, output paths, duration/format, validation, and any disclosure/consent requirement.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.