Skip to content
Agentmart
Submit a tool

voice-clone

Clone a voice using qwen3-tts and generate speech from text

Skill by Nuva-Lab

IndexedApache-2.0★ 6
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/nuva-lab-voice-clone

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Clone a voice using qwen3-tts and generate speech from text

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/voice-clone

What's inside

Skill name
voice-clone
Description
Clone a voice using qwen3-tts and generate speech from text
License
Apache-2.0
Instructions
36 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • clone.py
  • speak.py

SKILL.md (first lines)

# Voice Clone Skill

Use this skill to clone a speaker's voice and generate text-to-speech audio.

## Two-Step Process

### Step 1: Clone Voice (one-time)
```bash
python skills/voice-clone/clone.py <audio_sample.wav> [--transcript "text"]
```
Creates a speaker embedding file that can be reused.

### Step 2: Generate Speech
```bash
python skills/voice-clone/speak.py <embedding.safetensors> "Text to speak"
```
Generates audio using the cloned voice.

## Requirements

- FAL_KEY in .env (fal.ai API key)
- Voice sample: 10-30 seconds of clear speech (WAV/MP3)
- Optional: Transcript of the sample for better quality

## Output

- `assets/outputs/voice_embeddings/<name>_embedding.safetensors` - Reusable voice model
- `assets/outputs/audio/<name>_speech.wav` - Generated audio

## Notes

- qwen3-tts works best with Chinese speech samples
- Cross-lingual cloning (Chinese voice → English speech) may have quality variations
- Provide reference transcript for best quality

From Nuva-Lab/vibecut, Apache-2.0.

More from Nuva-Lab/vibecut

Signals

Stars
6
Forks
1
Open issues
0
Last commit (this folder)
Jan 30, 2026 (9 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/Nuva-Lab/vibecut
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Nuva-Lab

Cite this page

voice-clone skill. Agent Mart. https://agentmart.dev/skills/nuva-lab-voice-clone (last updated 2026-10-24)