Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Voice Cloning Local

ASecurity

Use when cloning a voice locally (offline, free, no API) from 3 seconds of reference audio with Qwen3-TTS. Triggers on "clonar voz local", "voice clone offline", "alternativa ElevenLabs grátis", "Qwen3-TTS", "TTS local Apache 2.0".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonbashgitapi

Works with

cliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill voice-cloning-local --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Voice Cloning Local?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Voice Cloning Local
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-voice-cloning-local/badge)](https://www.skillsdirectory.com/skills/majinmagros-voice-cloning-local)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: voice-cloning-local
description: Use when cloning a voice locally (offline, free, no API) from 3 seconds of reference audio with Qwen3-TTS. Triggers on "clonar voz local", "voice clone offline", "alternativa ElevenLabs grátis", "Qwen3-TTS", "TTS local Apache 2.0".
metadata:
  origin: ECC
  validated: 2026-08-22
  source_video: npVm4tBalp8
  official_sources:
    - https://huggingface.co/spaces/Qwen/Qwen3-TTS
    - https://github.com/Qwen-TTS/Qwen3-TTS
    - https://localaimaster.com/blog/qwen3-tts-local-setup (2026-08-16)
---

## Pipeline Qwen3-TTS (Voice Cloning Local)

Qwen3-TTS (Alibaba, Apache 2.0): **voice cloning** (3s de referência → qualquer texto), **voice design** (descrição natural), 10 idiomas, modelos 0.6B (1.8GB) e 1.7B (3.9GB) — roda em GPU consumer, 100% offline.

## Quando usar

- Clonar voz localmente sem API, grátis, offline
- Criar voz via descrição natural (idade, gênero, estilo)
- Batch de narrações com a mesma voz clonada
- Servidor local com Web UI para testes rápidos

## Quando NÃO usar

- Síntese genérica sem referência → use `fal-ai-media`
- Streaming TTS real-time ou 50+ idiomas (Qwen suporta 10)

### Validação Oficial (2026-08-22)
| Claim | Status | Fonte |
|---|---|---|
| Apache 2.0 | ✅ | HF model cards, GitHub LICENSE |
| Clone 3s / roda local (`pip install qwen-tts`) | ✅ | Base models, vLLM-Omni, ComfyUI |
| 10 idiomas | ✅ | Model card |
| Similarity 0.789 vs ElevenLabs 0.75/MiniMax 0.72 | ✅ | Benchmark (`references/benchmark-comparison.md`) |

---

## Passo a Passo

### 1. Ambiente

```bash
pip install -U qwen-tts          # simples; + FFmpeg; Python 3.10+, CUDA 4GB+ (0.6B) / 8GB+ (1.7B)
# Pesos manuais:
huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz --local-dir ./Qwen3-TTS-Tokenizer-12Hz
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base --local-dir ./Qwen3-TTS-12Hz-1.7B-Base
```

### 2. Clone / Design / Batch (scripts prontos em `scripts/`)

```bash
python scripts/voice_clone.py '<texto>' ref.wav '<transcrição EXATA do ref>' Portuguese 1.7B
python scripts/voice_design.py  # voz via descrição natural
python scripts/tts_cli.py clone "Texto" ref.wav "Transcrição" --lang Portuguese --model 1.7B
python scripts/tts_cli.py design "Texto" "young female, warm, Portuguese" --lang Portuguese
python scripts/batch_clone.py    # múltiplos textos, mesma voz
```

Regras: `ref_text` = match EXATO do áudio (crítico p/ qualidade); ref limpo 10-30s, 16kHz+; cross-lingual funciona mas pode vazar sotaque — prefira ref no idioma alvo.

### 3. Web UI local (`http://localhost:7861`, modelo em cache)

```bash

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →