omnivoice

Local TTS, voice cloning, voice design, and video dubbing via the VoiceStudio MCP server (open-source ElevenLabs alternative; nothing leaves the machine, runs on MPS/CUDA/CPU). Use when: (1) generating speech from text in any of 646 languages, (2) cloning a voice from a 3-second reference clip, (3) designing a voice by gender/age/accent/pitch/style, (4) dubbing a video into another language, (5) listing voice profiles or personality presets, (6) producing narration where privacy, cost, or absent API keys matter, (7) non-English narration where Edge TTS/kokoro fall short, (8) batch audio for blog posts or content pipelines. Triggers: 'omnivoice', 'voice clone', 'clone this voice', 'tts', 'narrate', 'generate speech', 'voice synthesis', 'dub video', 'voice design', 'local tts', 'multilingual voice', 'narrate this post', 'elevenlabs alternative'.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, executable skill body that offloads detail to real reference files and provides complete recipes with verification steps. Minor gains available in trimming a few verbose sections and making clone-verification error recovery explicit.

Suggestions

Add an explicit error-recovery branch to the clone workflow (e.g., 'if max < -20 dB, re-record closer to the mic or normalize') so the validate-fix-retry loop is spelled out.

Trim the dubbing 'web UI only' paragraph and inline benchmark figures, or move them into a reference file, to tighten conciseness toward anchor 5.

Consider a short batch-audio example with a validation step, since batch generation is promised in the description but not demonstrated in the body.

Dimension	Reasoning	Score
Conciseness	Dense with domain-specific knowledge Claude lacks (MCP internals, model lazy-download, terminal-buffering cue issue, clip-quality tips) and free of basic-concept padding, but a few sections (the dubbing web-UI paragraph, inline benchmark figures) could be trimmed — matching 'efficient; minor instances of over-explanation that could be trimmed' rather than the maximally lean anchor 5.	4 / 5
Actionability	Provides copy-paste-ready bash, ffmpeg, curl, and Python recipes covering the common cases (demo narration, save/convert WAV, voice clone end-to-end, voice design) — matching 'fully executable; copy-paste ready code or commands'.	5 / 5
Workflow Clarity	The clone recipe has a clear sequence with explicit validation (volumedetect 'max should be > -20 dB', afplay verification, script playback-for-verification) and a tips checklist, but error-recovery feedback (what to do when the threshold fails) is implied rather than spelled out — 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	Well-structured overview (Task Index, Common Workflows, When NOT to use) with one-level-deep references to real, verified files (references/engines-comparison.md, references/mcp-setup.md, scripts/*.sh), each clearly signaled and described in a Resources section — matching the anchor-5 example.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: third-person, concrete, comprehensive, with explicit 'what' and 'when' guidance plus a rich trigger-term list. It distinguishes itself clearly from generic TTS skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'generating speech from text in any of 646 languages', 'cloning a voice from a 3-second reference clip', 'designing a voice by gender/age/accent/pitch/style', 'dubbing a video' — covering the domain comprehensively, matching the anchor-5 example.	5 / 5
Completeness	Explicitly answers both 'what' (Local TTS, voice cloning, voice design, video dubbing via VoiceStudio MCP server) and 'when' (a numbered 'Use when:' list of 8 scenarios plus trigger phrases), matching the anchor-5 example exactly.	5 / 5
Trigger Term Quality	A dedicated 'Triggers:' list supplies natural phrases users would say ('voice clone', 'clone this voice', 'tts', 'narrate', 'generate speech', 'dub video', 'elevenlabs alternative') with synonyms, matching comprehensive anchor-5 coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (local, open-source ElevenLabs alternative via a named MCP server) with distinct triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: debpalash/OmniVoice-Studio
Path: .claude/skills/omnivoice/SKILL.md
Commit: 98c9e68

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.