voice-realism
voice-realism is an Audio, music & podcasts skill for AI agents, published by nestyme in the awesome-prompts repository on GitHub. Skillspace rates voice-realism D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Rewrite AI video / text-to-speech prompts so the generated VOICE sounds like a real human, not a robot. Takes any video prompt (Veo, Seedance, Kling) or TTS script (ElevenLabs) with spoken lines and returns (1) a rewritten prompt with emotion, delivery, acoustics, and framing baked in — parameters like whisper, sighs, laughs, tone words are chosen automatically from scene context — and (2) a post-processing checklist to strip the remaining AI polish. Use this skill whenever a prompt contains dialogue, a talking head, a voiceover, narration, or any character who speaks — even if the user only asks to "improve" or "fix" the prompt and doesn't mention voice. Also use it when the user complains that generated speech sounds robotic, synthetic, flat, or "AI-like".
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 88
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 99 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.