Piper TTS · ffmpeg · FastAPI

Script to video,
fully automated.

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

✍️ScriptPlain text input
🎙️VoicePiper TTS
🎬BackgroundPick video
📝SubtitlesAuto-timed SRT
▶️ExportMP4 output
5-step pipeline · each step independently callable via REST

Everything you need to ship video content

🌐
Multilingual TTS

Vietnamese and English voices — male and female — powered by local Piper models. No external API calls.

⏱️
Auto-synced subtitles

SRT files timed to actual voice duration, not raw text length — always perfectly aligned.

🎨
Subtitle styles

Named style presets control font, size, color, bold, position, and max chars per line.

🔁
Looping backgrounds

Background videos loop seamlessly if shorter than the voice. Output always stops at voice end.

FastAPI backend

Every pipeline step has its own REST endpoint. A /options route feeds all frontend dropdowns.

🗂️
Config-driven

All models, paths, and style dicts live in config.py — one source of truth, nothing hardcoded.

REST API

Integrate in minutes

Call /options first to fetch available voices, styles, and backgrounds. Then POST to each pipeline step independently.

See live demo →
# 1. Get options
GET /options
# 2. Generate voice
POST /voice/generate
{
  "script": "Xin chào!",
  "lang": "vi",
  "gender": "female"
}
# 3. Render video
POST /video/render

Ready to make your first video?

Sign up free and get 100 credits to start. No credit card needed.