Lumoz Voice Cloning & Multilingual TTS

Clone any human voice from a 10–120s audio sample and synthesize expressive speech in 90+ languages via MCP

Install Lumoz Voice Cloning & Multilingual TTS
npx lumoz-skills add lumoz-voice-cloning

Adds SKILL.md and references to .agents/skills/lumoz-voice-cloning/.

https://lumozai.com/api/mcp

Connect Lumoz MCP once in Claude to get Lumoz Voice Cloning & Multilingual TTS and every LumozAI skill automatically (lumoz_get_skill("lumoz-voice-cloning")). Setup guide →

git clone https://lumozai.com/models/lumoz-tts .agents/skills/lumoz-voice-cloning

Clones the pinned, NVIDIA SkillSpector-verified mirror with all scripts and references.

Category
Media & Motion
Security
NVIDIA SkillSpector Passed
License
MIT (Free)
Compatible Runtimes
Antigravity, Claude Code, Cursor, Windsurf

Lumoz Instant Voice Cloning & Multilingual TTS

Yes! Lumoz AI natively supports Instant Voice Cloning (lumoz_clone_voice) and 90+ language Text-to-Speech (lumoz_generate_tts) directly through MCP.

1. How to Clone a User's Voice in MCP

If the user uploads or provides an audio recording of their voice (10 to 120 seconds of clean speech in MP3, WAV, or M4A):

Option A: Permanent Reusable Voice Clone (lumoz_clone_voice)

  1. If the user's audio is a local file or chat attachment, first upload it to Lumoz R2 CDN using lumoz_upload_media (pass the base64 data URI).
  2. Call lumoz_clone_voice:
    {
      "name": "User Custom Voice",
      "audio_url": "https://cdn.lumozai.com/uploads/...",
      "remove_background_noise": true,
      "sample_text": "Hello, this is an instant preview generated with Lumoz Voice Cloning."
    }
    
  3. lumoz_clone_voice returns a permanent white-label voice_id (e.g. "lumoz-voice-user-custom-a8f2k").
  4. Pass that voice_id into lumoz_generate_tts for all future voiceovers!

Option B: 1-Step Instant Clone & Speak (lumoz_generate_tts with reference_audio)

You can also pass reference_audio directly inside lumoz_generate_tts (or lumoz_run_model with model_id: "lumoz-tts"):

{
  "text": "[warmly] Hello and welcome! This entire voiceover was synthesized using my own cloned voice.",
  "reference_audio": "https://cdn.lumozai.com/uploads/..."
}

2. Directing Emotion & Merging with Video

  • Inline Emotion Tags: Use bracketed cues in text such as [whispers], [excited], [calmly], [laughs], or [narrator tone].
  • Merging Voiceover into Video: Once lumoz_generate_tts returns the audio_url, call lumoz_run_microservice with service: "video-audio-merger", video_url, and audio_url to combine the cloned voiceover with any video!

Frequently asked questions about Lumoz Voice Cloning & Multilingual TTS

What does the Lumoz Voice Cloning & Multilingual TTS AI agent skill do?

Complete workflow for cloning custom voices with Lumoz Instant Voice Clone v4 (`lumoz_clone_voice`), uploading local voice samples via `lumoz_upload_media`, and generating expressive 90+ language voiceovers with `lumoz_generate_tts` and `video-audio-merger`.

How do I install Lumoz Voice Cloning & Multilingual TTS in Claude Code, Cursor, or Antigravity?

Run `npx lumoz-skills add lumoz-voice-cloning` in your project root, or clone https://lumozai.com/models/lumoz-tts into `.agents/skills/lumoz-voice-cloning`. Compatible runtimes (Antigravity, Claude Code, Cursor, Windsurf) discover `.agents/skills/lumoz-voice-cloning/SKILL.md` automatically.

Is Lumoz Voice Cloning & Multilingual TTS verified and safe to run?

Yes. Lumoz Voice Cloning & Multilingual TTS passed NVIDIA SkillSpector security inspection with 0 critical or high findings and is pinned to immutable commit v4.0.0 under LumozAI-com.

Can AI agents fetch Lumoz Voice Cloning & Multilingual TTS automatically via MCP or REST API?

Yes. Agents connected to Lumoz MCP can call lumoz_get_skill("lumoz-voice-cloning"), or any pipeline can fetch raw Markdown from https://lumozai.com/api/skills/lumoz-voice-cloning/raw.