ysskrishna logoysskrishna
AI Video Dub Generator logo

AI Video Dub Generator

Same YouTube clip. A new language track. You run the pipeline yourself.

Gallery image 1
Gallery image 2
Gallery image 3
Get it
Built with
AI Apps & Assistants
Voice & Speech
Speech to Text
OpenAI
TypeScript
React
FastAPI
Voice AI
Python
Node.js
SQLite
Deepgram
ElevenLabs
Details
FreeMIT licenseCreated October 11, 2025Updated November 12, 2026
Share this product

Your audience speaks another language. Your video does not.

You finished the explainer. It is clear in English. Then someone asks for Hindi, or Spanish, or French. Re-recording is slow. Paying a studio per language adds up fast. Pasting subtitles alone is not always enough when people want to hear the story.

AI Video Dub Generator is a self-hosted app that takes a YouTube-style source, builds a new language track, and hands you a dubbed file while you watch progress in the browser.

One link in. A dubbed clip out. You stay in control.

What you get

  • A full dubbing run from a video link. Point at a supported source, choose a target language, and let the pipeline transcribe, translate, synthesize speech, and assemble the result.
  • Dozens of target languages. The project lists support for more than thirty languages so you can test the same clip in more than one market.
  • Live job status instead of blind waiting. Long runs report progress in the web interface so you know whether a job is still working or ready to review.
  • A browser UI for starting and watching jobs. A responsive web client pairs with a backend that stores job state, so you are not living in terminal logs alone.
  • Example outputs to judge quality first. The repository ships sample dubbed clips you can watch before you commit your own footage.
  • Free and open source code. MIT licensed. You host it. Usage costs depend on the speech, translation, and voice services you connect.

Picture your Tuesday afternoon

For example, you paste a link to a ten-minute tutorial. You pick a target language and start the job. You keep the tab open, glance at status updates, then open the finished file and listen before you publish anywhere. If the pacing feels off, you treat it as a draft, not a broadcast master.

Ready to try it?

  • Get it on GitHub for setup steps in the backend and client README files
  • Browse example dubbed videos linked from the same repository when you want a quality reference

Frequently asked questions

Why not just use HeyGen, VEED, or another all-in-one dubbing site?

Those tools are built to hide the steps and run in their cloud. This project is for when you want the pipeline on your machine, your API accounts, and a UI you can extend. You trade convenience for control and you accept setup work up front.

How do I dub a YouTube video into another language automatically?

Clone the repository, add the API keys the README asks for, start the backend and web client, then submit a video source through the app. The README describes separate setup guides for the server and the interface.

What languages can AI video dubbing support here?

The README cites more than thirty target languages. Check the project docs when you run it for the list that matches your build.

What do I need to set up a self-hosted dubbing app?

You need current Node.js and Python versions as listed in the README, plus valid API keys for the speech, translation, and voice services the project integrates. Follow the nested README files for the backend API and the web client.

How do I track progress when a long dub job is running?

The README highlights real-time job monitoring with live status updates in the application. Use the web UI to see where a run stands instead of guessing from silence.

Is it free?

The project code is open source under the MIT license. Running dubs is not automatically free: your speech, translation, and voice providers bill on usage, and quotas are theirs.

Why not just stitch together transcription, translation, and text-to-speech APIs myself?

You can. This app already wires those stages, adds job tracking, and gives you a UI to start runs and review outputs. You still supply keys and you still own copyright and platform rules.

Do I need perfect lip sync for YouTube dubbing?

Not always, but expectations matter. The product page limits note that quality, lip sync, and naturalness can vary by clip and provider. Listen and watch before you publish, and respect copyright, platform terms, and voice licensing.

Continue exploring

ProductAI Healthcare Assistant

AI Healthcare Assistant

Rehearse patient conversations at your desk. Text or voice in, scored feedback back.
Voice & Speech
AI Apps & Assistants
Speech to Text
Voice AI
BlogCover image for 17 Thinking Skills for AI Agents: Pre-Mortem, Five Whys, Six Hats and More

17 Thinking Skills for AI Agents: Pre-Mortem, Five Whys, Six Hats and More

AI Apps & Assistants
Agent Skills
4 min read
ToolCover image for AI Token Counter

AI Token Counter

AI token counter with model pricing and context-window comparison in your browser.

Chat & AI
AI Apps & Assistants
+1
CourseCover image for Prompt Engineering for Coding Agents

Prompt Engineering for Coding Agents

Write prompts that coding agents act on: clear goals, the right context, output contracts, examples, structured thinking, shorter answers and a tiny eval set.

Agent Skills
Chat & AI

8 chapters · 21 min

BlogCover image for How to Install Caveman in Cursor and Claude Code

How to Install Caveman in Cursor and Claude Code

AI Apps & Assistants
Agent Skills
+1
3 min read
Productskills.sh+1Claude Code Subagents for Cursor

Claude Code Subagents for Cursor

Your Cursor subagents can finally run on the model you picked in each agent file.
Chat & AI
Agent Skills
AI Apps & Assistants
Bash