skills.rest
opensquilla
opensquillaOFFICIAL
Explore all skills by this author →
WebsiteGitHub

voice-conversion-studio

Convert local audio recordings into authorized target voices using a configured audio provider.

6.8k|540|Updated May 6, 2026
Search Tags:#narration#consent#text to speech#voice conversion#Localization#Audio#voice changer
One-click install
npx skills add https://github.com/opensquilla/opensquilla --skill voice-conversion-studio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice-conversion-studio
Source: https://github.com/opensquilla/opensquilla/tree/main/src/opensquilla/skills/bundled/voice-conversion-studio
Command: npx skills add https://github.com/opensquilla/opensquilla --skill voice-conversion-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converting an existing recording into a different voice requires navigating provider capabilities, consent and copyright rules, and locale/accent quality concerns. This Skill standardizes that workflow so voice conversion requests are triaged, rights-checked, and executed through the proper audio provider tool.

Core Features & Use Cases

  • Rights-First Conversion Workflow: Verifies source recording copyright, speaker consent, and target voice authorization before calling the voice_convert tool, and refuses public figure or copyrighted character imitation.
  • Preview-First Quality Control: Converts a short sample before processing full recordings to catch accent transfer issues, background noise, or dialect mismatches.
  • Structured Tool-Result Handling: Interprets voice_convert statuses (ok, consent_required, not_available) and returns provider, target voice, output path, mime type, and a rights summary.
  • Use Case: A content creator wants to convert their own Mandarin narration into a licensed English commercial voice. The Skill confirms consent, runs a short preview to validate accent transfer, then converts the full recording and returns a playable audio artifact.

Quick Start

Convert my local recording narration.wav into the licensed target voice 'calm-narrator' and give me a short preview first.

Frequently Asked Questions about voice-conversion-studio

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert an audio recording to a different voice?▼

Provide a local source recording and an authorized target voice, then the Skill calls the voice_convert tool with the source audio, voice ID, and optional output path. It returns a playable audio artifact along with provider, mime type, and rights summary.

What consent is required for voice conversion?▼

Both sides need authorization: the source recording requires speaker consent and copyright clearance, and the target voice must be provider-licensed, a consented cloned voice, or a user-provided voice ID. If consent is missing, the tool returns consent_required and the conversion stops.

Can I convert audio to sound like a celebrity or fictional character?▼

No. The Skill refuses conversions targeting public figures, celebrities, politicians, or copyrighted characters. It instead offers non-identifying alternatives such as a mature calm narrator or bright commercial voice.

Why does voice conversion produce odd accents in multilingual audio?▼

Odd accent transfer happens when the target voice does not natively support the target language, or when the source has strong dialect, background music, reverb, or heavy code-switching. Converting a short preview first catches these issues before processing the full recording.

What happens when the voice_convert tool returns not_available?▼

The Skill quotes the provider's note and distinguishes the cause: provider setup problems, feature gating, API key or quota limits, unsupported file formats, or invalid source paths. It does not retry with a different voice identity.

Related Skills

Explore More Content & Communication Skills→
video-production-buddyvideo-production-buddy
602

music

Generate custom, copyright-free music via the ElevenLabs Music API.

Official
Intermediate
clinecline
19

save-to-spotify

Convert text sources into TTS-narrated Spotify podcast episodes with chapters.

Official
Advanced
sepivipsepivip
270

translate

Translate text between languages with automatic source detection and pronunciation hints.

Community
Intermediate
AIDotNetAIDotNet
84

text-to-speech

Convert input text into speech audio files using pyttsx3.

Official
Basic