nuva-lab/voice-clone
skills/voice-clone/SKILL.md
Clone a voice using qwen3-tts and generate speech from text
$ install --global
skillsauthnpx skillsauth add nuva-lab/vibecut voice-cloneInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:41 PM1.8s1 file scanned
SKILL.md
- name:
- voice-clone
- description:
- Clone a voice using qwen3-tts and generate speech from text
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)
python skills/voice-clone/clone.py <audio_sample.wav> [--transcript "text"]
Creates a speaker embedding file that can be reused.
Step 2: Generate Speech
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 modelassets/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
Related Skills
nuva-lab/write-script
tools
VerifiedTrustedCommunity
Generate voiceover scripts in Joyce's style for video clips
5SKILL.mdUpdated Apr 9, 2026
nuva-lab/skills/validate-media
development
VerifiedTrustedCommunity
# Validate Media Skill Pre-flight media validation and diagnostics using ffprobe. ## Purpose Check video/audio files for common issues before rendering: - Duration mismatches between video and audio tracks - Missing audio tracks - Codec compatibility - Volume levels - Potential freeze points ## Usage ```bash python skills/validate-media/validate.py <video_file> [--verbose] ``` ## Output JSON report with issues and recommendations: ```json { "file": "video.mp4", "video_duration": 35.1
5SKILL.mdUpdated Apr 9, 2026
nuva-lab/transcribe-clip
tools
VerifiedTrustedCommunity
Transcribe a video clip using Gemini to get timestamped segments for captions
5SKILL.mdUpdated Apr 9, 2026
nuva-lab/transcribe-audio
testing
VerifiedTrustedCommunity
ASR with ~30ms timestamp precision using Qwen3-ASR + ForcedAligner
5SKILL.mdUpdated Apr 9, 2026