ForkFree

Video and audio

dubsmith

by tamanois

Dubsmith is a command-line tool that dubs a video or audio file into another language while keeping each speaker's own voice. It can also generate speech from text using saved, designed or cloned voices, and produce subtitles on their own.

Proof level: ReadNew and promisingApache-2.0

Get it on GitHubCompare

No demo yet

Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.

The catch

New and promisingUnder two months old. Expect rough edges and fast changes.

Check this first: A GPU with about 12 GB of VRAM is strongly recommended; CPU-only use will be slow.

Things to check

  • A GPU with about 12 GB of VRAM is strongly recommended; CPU-only use will be slow
  • Needs an OpenAI-compatible LLM endpoint for translation, which may be a paid cloud service unless you run a local model
  • Large downloads: about 10 GB of models, plus 3–11 GB per optional expressive backend
  • Voice cloning can be misused; model licences differ and should be checked before commercial use
  • Very new project with no stars yet
  • Lip sync and multi-language source videos are not supported

Can you use dubsmith commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

What can you do with dubsmith?

  • Dub a video into one of ten languages while keeping each speaker's own voice
  • Generate subtitles (SRT, soft-embedded or burned in) in another language without dubbing
  • Create speech from text using a designed, cloned or saved voice, with per-line emotion

How do you get dubsmith running?

Clone the repository, create a Python 3.10–3.12 virtual environment, run pip install, download about 10 GB of models, and point it at an OpenAI-compatible LLM endpoint; an optional Dockerfile is provided.

Follow the official instructions in the project README.

Make money with it

Offer video localisation as a freelance service, dubbing creators' or small businesses' videos into other languages.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Localise training, marketing or explainer videos into other languages without paying per-minute dubbing fees
  • Produce voiceovers and subtitles for client videos using a consistent saved voice

Checked 12 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.

Similar tools in Video and audio

VoiceStudio debpalash
Worth a look

VoiceStudio is a desktop, mobile and Docker app that runs speech tools on your own device. It clones and designs voices, dubs videos, transcribes and dictates speech, and turns text into audiobooks in many languages.

Instead of ElevenLabsUp to $72 a year

Proof level: Read 94.8k stars +1527 a day AGPL-3.0
hyperframes heygen-com
Worth a look

HyperFrames is an open-source framework that turns HTML, CSS, media and animations into MP4 videos. It is designed so AI coding agents, or people using a command line, can write a page and render it as a video.

Instead of Remotion

Proof level: Read 87.2k stars +570 a day Apache-2.0
lemo-opuscar lemomo-ai
New and promising

Lemo-Opuscar is a tool for creating films using code, offering 59 pre-made styles or the ability to create your own. It is designed for use with Claude Opus 5.5 and can be installed as a plugin or cloned from GitHub.

Instead of Adobe Spark Video

Proof level: Read 13.8k stars +414 a day MIT