Turn a topic, your own script or your own voice recording into a finished faceless video: a voice, matching footage, word-by-word captions and upload text. It runs on your own Windows, Mac or Linux computer.

What it does

• Text to video: an AI writer drafts the script in one of 9 formats, from 20 seconds to 2.5 minutes. Free options: Gemini, Groq or Ollama. You check every scene before it renders.
• 28 built-in voices run on your computer at no cost. OpenAI and ElevenLabs voices work with your own key.
• Captions timed word by word, in 4 styles, plus an .srt file.
• Footage that fits: your own clips, Pixabay (free key), Pexels (your key) or public-domain photos (no key). A picture check and an AI title check drop off-topic clips.
• 9:16, 16:9 or 1:1 at 30 fps, sound levelled to -14 LUFS.
• Batch: paste up to 100 topics and they render one after another.

One-time purchase: no subscription or credits. Download it and keep it.

Needs Node.js 20 or newer (free), 8 GB of memory recommended and about 1.5 GB of disk space.

Try the free edition first: the same studio, with videos up to 30 seconds and a small watermark.

Founding offer: code FOUNDING takes 20% off the full edition until 30 November 2026, for the first 100 orders.

A tool for making videos, not an income promise. YouTube doesn’t pay for mass-produced, repetitive videos, so review and improve each one.