Voice cloning. Only clone voices you own or have permission to use.
Who it is forA teacher or marketer making tutorials who does not want to record narration again for every edit.
The problemRe-recording voice-overs for every script change is slow, and cutout tools usually need cloud uploads.
The outcomeA tutorial with narration in your own cloned voice, a cut-out presenter and clean audio, made locally.
What you need first
- macOS, Windows, Linux or Android (iOS sideloaded)
- AI models for captions, voices and cutout download once from Settings, then work offline
- To build from source: Rust 1.93+, FFmpeg 7+ development libraries, cmake and a C++ compiler
Steps
- Install Concat and download the voice and cutout models from Settings
- Clone a voice from a few seconds of your recording, or pick a free local voice
- Generate the narration with text-to-speech from your script
- Remove the background from your webcam footage and place it over the screen recording
- Use one-switch voice cleanup to denoise and level loudness, then export
Prompt for your agent
Plan a tutorial edit in jub0t/Concat for <topic>: write the narration script, list the steps to clone my voice and generate the voice-over, remove my webcam background, and arrange it picture-in-picture over the screen recording.
Caveat.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for jub0t/Concat and "Make a tutorial with a cloned voice-over and background removal"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer