Write a script, pick a voice and background — Veta handles the rest. Timed subtitles, looping video, ffmpeg rendering, done.
Free to start · 100 credits on signup · No credit card required
Vietnamese and English voices — male and female — powered by local Piper models. No external API calls.
SRT files timed to actual voice duration, not raw text length — always perfectly aligned.
Named style presets control font, size, color, bold, position, and max chars per line.
Background videos loop seamlessly if shorter than the voice. Output always stops at voice end.
Every pipeline step has its own REST endpoint. A /options route feeds all frontend dropdowns.
All models, paths, and style dicts live in config.py — one source of truth, nothing hardcoded.
Call /options first to fetch available voices, styles, and backgrounds. Then POST to each pipeline step independently.
Sign up free and get 100 credits to start. No credit card needed.