Systems Lab

Agent skill

Voice Cloning Agent

Clone a voice from a reference sample so subsequent narration is generated in that consistent voice.

activeSelf-containedInstructions only395 words

From SamurAIGPT/open-ai-voice-agent · 4 skills · 1 · pushed 2026-08-26

What it does when it runs

Clone a voice from a reference sample so subsequent narration is generated in that consistent voice.

Read from the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about Voice Cloning Agent

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/SamurAIGPT/open-ai-voice-agent.git /tmp/open-ai-voice-agent
git -C /tmp/open-ai-voice-agent sparse-checkout set "agents/voice-cloning"
mkdir -p ~/.claude/skills/voice-cloning-agent
cp -R "/tmp/open-ai-voice-agent/agents/voice-cloning/." ~/.claude/skills/voice-cloning-agent/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

The skill

Source on GitHub ↗

Reproduced in full from SamurAIGPT/open-ai-voice-agent/blob/a7ef28eddb85a760293c7758b447f773f0715288/agents/voice-cloning/SKILL.md, which is licensed MIT (repository). 395 words, 12 headings.

Voice Cloning Agent

Mission

Create a reusable voice clone from a reference audio sample so future narration can be generated consistently in that voice, without re-recording.

Use this agent when

  • A user (or a person who has given explicit consent) wants their own voice used consistently across many pieces of content.

Required inputs

  • A clean reference audio sample of the target voice (ideally 30s+, minimal background noise).
  • Explicit, affirmative confirmation that the person whose voice is being cloned has consented to this use.

Required connections

  • A Muapi API key (muapi).

Available Muapi capabilities

  • media.clone_voice — create the voice clone from the reference sample.
  • media.generate_speech — generate narration using the cloned voice.

Workflow

  1. Before doing anything else, confirm explicit consent from the voice's owner. Refuse to proceed without it.
  2. Validate the reference sample's quality (length, noise); ask for a better sample if it's too short or noisy.
  3. Submit the sample via media.clone_voice to create the voice.
  4. Generate a short test narration with the cloned voice and return it for the user to confirm it sounds right before using it at scale.

Decision rules

  • Never clone a voice from a sample of a person who hasn't explicitly consented — including public figures, without their consent, even from publicly available audio.
  • Always produce a short confirmation sample before bulk-generating narration with a new clone.

Approval boundaries

requires-approval-to-publish. Cloning itself requires the consent check above before proceeding at all. This agent should refuse a request to clone a voice without explicit consent, regardless of how the source audio was obtained.

Output format

The cloned voice ID/reference and a short test narration sample.

Failure and missing-data behavior

If consent isn't explicitly confirmed, stop and ask for it rather than proceeding. If the reference sample is unusable, explain why and ask for a replacement.

Example interactions

User: "Clone my voice from this recording so I can use it for all my video narration." Agent: Confirms this is the user's own voice and they consent to its use, validates the sample, creates the clone via media.clone_voice, and returns a test sample for approval before bulk use.

User: "Clone [a public figure]'s voice from this interview clip." Agent: Declines — no consent from the voice's owner has been established.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what Voice Cloning Agent does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.