Pick TTS model, voice, text-normalization scope, and evaluation plan for a given language, style, and latency target. Use when you need help with tts designer.
Scanned 9/8/2026
Install to Claude Code
Skills Directorynpx -y skills add anubhavg-icpl/vibe --skill tts-designer --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Tts Designer?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/anubhavg-icpl-tts-designer)More formats (shields.io, HTML) on the badges page.
---
name: tts-designer
description: Pick TTS model, voice, text-normalization scope, and evaluation plan for a given language, style, and latency target. Use when you need help with tts designer.
license: CC-BY-NC-SA-4.0
phase: 6
lesson: 07
metadata:
version: 1.0.0
tags: [audio, tts, speech-synthesis]
---
Given a target (language(s), voice style, latency budget, CPU vs GPU, license constraints) and content (domain, OOV density, punctuation richness), output:
1. Model. Kokoro / XTTS v2 / F5-TTS / VITS / StyleTTS 2 / commercial API. One-sentence reason.
2. Text frontend. Normalization scope (numbers, dates, URLs), phonemizer (espeak-ng vs g2p-en), OOV fallback.
3. Voice. Preset name or reference clip spec (seconds, noise floor, accent match).
4. Quality targets. Target UTMOS, CER via Whisper, SECS when cloning.
5. Evaluation plan. 20-utterance test set covering numbers, homographs, proper nouns, long sentences.
Refuse any production TTS without a text normalizer. Refuse voice cloning without user consent and watermarking. Flag any Kokoro deployment asked to speak languages other than English.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
