Skip to content
Skillpedia
Agents48k · #4518

voice-cloning-studio

Allows your agent to clone voices for use in projects. Useful for creating personalized audio professionally.

What it does

This tool lets you create a copy of your voice or a brand's voice using a clean audio sample. You can name this voice and test it quickly. It's a paid service that runs on the Beatra platform.

When to use it

  • ✓When you want to create a custom voice for use in projects.
  • ✓When you need a consistent brand voice for marketing materials.
  • ✓When you want to test voice creation before committing to the paid service.

Example of what to ask your AI

“I want to create a voice from my audio and name it 'My Clear Voice'.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/sickn33/agentic-awesome-skills/blob/main/plugins/agentic-awesome-skills-claude/skills/voice-cloning-studio/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/sickn33/agentic-awesome-skills/blob/main/plugins/agentic-awesome-skills-claude/skills/voice-cloning-studio/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

First, you download and verify a secure software package. Then, you authorize the use of the paid Beatra service. Finally, you upload audio to create and test your new voice.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add sickn33/agentic-awesome-skills --skill voice-cloning-studio

Or download just the file:

curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/voice-cloning-studio/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

AI Voice Cloning Skill

Overview

Create a reusable personal or brand voice from a clean audio sample, give it a memorable name, and hear it in a short test reading, from inside Claude Code, Codex, or OpenClaw. The work is produced on the hosted, paid Beatra service (mcp.beatra.ai).

This catalog entry is a reviewed pointer, not the executable package. It contains no client code and performs no Beatra operation by itself. The package it points to bundles three standard-library Python scripts that make network calls, store a credential, and can replace their own files. Read Install and Security & Safety Notes before activating it.

Pinned identity Value
Package voice-cloning-studio 0.2.1
Archive https://cdn.beatra.ai/agent-packages/voice-cloning-studio/v0.2.1/voice-cloning-studio-skill-0.2.1.zip
Archive SHA-256 38299679b429aa73ce5d514c3e314e77330d7c6d663e480a9d982dd852a428a2
Source tree beatra-ai/ai-voice-cloning-skill@64923d9 (full SHA 64923d96ecdd1adce28ad4ad264b3808dda0ce2d)
License MIT No Attribution (MIT-0)

The archive holds regular files only (no symlinks, no executable bits, no binaries). Confirm that with the inspect commands below. Every file must be byte-identical to the source tree at the pinned commit.

When to Use This Skill

  • Use when the user explicitly wants a reusable custom voice enrolled on Beatra and accepts that it is paid.
  • Use only after the speaker (or rights holder) attests they own the sample and approve enrollment.
  • Do not use to clone a voice without documented owner consent.

Install (pinned, verified, approved twice)

Step 1: Download and verify into a review directory

Explain that this downloads an external package from cdn.beatra.ai, then ask for approval. Only after approval:

umask 077
review_dir="$(mktemp -d)"
cd "$review_dir" || exit 1
curl -fsSLO "https://cdn.beatra.ai/agent-packages/voice-cloning-studio/v0.2.1/voice-cloning-studio-skill-0.2.1.zip"
printf '%s  %s\n' \
  '38299679b429aa73ce5d514c3e314e77330d7c6d663e480a9d982dd852a428a2' \
  'voice-cloning-studio-skill-0.2.1.zip' | shasum -a 256 -c -

Stop if the check does not print OK. The expected digest comes from this catalog entry, not from a file on the same CDN.

Step 2: Inspect before activation

unzip -l voice-cloning-studio-skill-0.2.1.zip
unzip -q voice-cloning-studio-skill-0.2.1.zip
find voice-cloning-studio -type l -print            # expect no output
find voice-cloning-studio -type f -perm -111 -print # expect no output
grep -n '"auto_update": True' voice-cloning-studio/scripts/mcp_client.py

Optionally confirm byte identity with the public source tree (a second, independent host):

git clone --quiet --filter=blob:none --no-checkout https://github.com/beatra-ai/ai-voice-cloning-skill.git src
git -C src checkout --quiet 64923d96ecdd1adce28ad4ad264b3808dda0ce2d -- skills/voice-cloning-studio
(cd voice-cloning-studio && find . -type f | LC_ALL=C sort | xargs shasum -a 256) > archive.sha
(cd src/skills/voice-cloning-studio && find . -type f | LC_ALL=C sort | xargs shasum -a 256) > tree.sha
cmp archive.sha tree.sha && echo IDENTICAL

Report to the user what the review found: SKILL.md, manifest.json, the bundled Markdown references, and scripts/authorize.py, scripts/mcp_client.py, scripts/uninstall.py (Python 3.10+, standard library only, no dependency installation, no lifecycle hooks). Summarize the network, credential, local-state, telemetry, and self-update behavior listed under Security & Safety Notes.

Step 3: Copy in and disable self-update before any other command

Ask for a second, separate approval, because this changes agent configuration. Then copy the reviewed tree to the host's skills directory (Claude Code shown; use the equivalent path for other hosts) and immediately turn off silent self-update for that exact path:

dest="$HOME/.claude/skills/voice-cloning-studio"
test ! -e "$dest" || { echo "destination exists; stop and ask the user"; exit 1; }
cp -R voice-cloning-studio "$dest"
python3 "$dest/scripts/mcp_client.py" update --auto off

The last command must print Automatic Beatra package updates are disabled. It writes only

…

FAQ

Is it safe to use this tool?

Yes, the package is verified and approved. You need to review and approve the installation and usage steps, especially those involving costs.

Do I have to pay to use it?

Yes, creating and using the voice is done on a paid service called Beatra. The tool shows you the costs before you approve any action.

Can I clone anyone's voice?

No, you can only clone voices if you have explicit permission from the audio owner or copyright holder. Misuse is not allowed.

Details

Original description by the author

Install and use the official AI Voice Cloning package, pinned by digest, for paid hosted work on the Beatra service.

repo: sickn33/agentic-awesome-skills

Popularity

GitHub stars
48k
Ranking position
#4518
License
MIT
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills