voice-clone SKILL.md skillA
voice-clone from puntorigen/avatar-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add puntorigen/avatar-skills/voice-clone@git:20260709.ec45941Pins git:20260709.ec45941 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- puntorigen/avatar-skills
- Path
voice-clone/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260709.ec45941, committed Jul 9, 2026
- Size
- 8,989 bytes
- Repository stars
- 6
- License
- MIT
Clone a narrator's voice from a clean voice audio file using MiniMax voice-cloning on Replicate, then generate new speech (TTS) in that cloned voice with MiniMax speech-2.8-hd. Cloning takes the clean voice MP3/WAV (e.g. voice_concat.mp3 from the voice-isolate skill), trains a voice (default speech-2.6-hd) and saves voice_id + a preview under <avatar>/voices/<name>.json. Generation reuses the avatar's trained voice (or trains one if missing), auto-detects the text language for MiniMax's…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Voice Clone Two capabilities, one skill: 1. **Clone** a narrator's voice with **MiniMax voice-cloning** → a reusable **`voice_id`** saved in the avatar folder. 2. **Generate** new speech in that cloned voice with **MiniMax `speech-2.8-hd`**, saved under `<avatar>/generated-audios/` with a manifest. The clone input is a clean voice file — ideally `voice_concat.mp3` produced by the `voice-isolate` skill. ## Requirements - `pip3 install -r requirements.txt` (`replicate` client + `langid` for language detection). - A Replicate API token. It is **shared** with the other Replicate skills (avatar-video-reel, gpt-image-2, bg-music, …) and discovered automatically. To set/refresh it: `python3 scripts/setup_key.py YOUR_REPLICATE_API_TOKEN`. - The voice file must be **MP3/M4A/WAV, 10s–5min, <20MB**. - A local tunnel — **`cloudflared`** (preferred) or **`ngrok`** — installed on PATH (**only for cloning**, not for generation). `brew install cloudflared` (no account needed) or `ngrok config add-authtoken <token>` once. See *How the upload works* below. ## How the upload works `minimax/voice-cloning` re-fetches the audio from MiniMax's own servers, so it …
Read the whole file at its exact version.
How to install
mdr add puntorigen/avatar-skills/voice-clone@sha256:90d9193f6cc64a2dThe line at the top of this page pins the label git:20260709.ec45941, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_dcgvjktyljdvn3iz)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 9, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8989 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
puntorigen/avatar-skills · 6 stars · license MIT · pushed 2026-09-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dcgvjktyljdvn3iz GET https://markdownregistry.com/api/v1/resolve?ref=puntorigen/avatar-skills/voice-clone GET https://markdownregistry.com/api/v1/blob/90d9193f6cc64a2d52ac9e371377225590adfe512a0178dc7a7898076a716bbd
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from puntorigen/avatar-skills
Every file in puntorigen/avatar-skills