Generate reels and YouTube videos from text. Automated voiceover, word-level karaoke captions, B-roll, transitions, and effects. All from code or API.
Write Script
Plain text, any language
Generate Voice
Edge TTS, ElevenLabs, or OpenAI
Auto Captions
whisper.cpp word-level timing
Render Video
Remotion + effects = MP4
Write your script, pick a voice, and get a finished reel with captions, transitions, and music. Full TTS + whisper pipeline built in.
Word-by-word highlighting with pixel-accurate timing from whisper.cpp. Bold, clean, neon, or custom styles.
Text cards, B-roll cutaways, punch-in zoom, highlight boxes, animated counters, lower thirds, CTAs, PiP, and more.
Two compositions: 9:16 vertical reels and 16:9 horizontal YouTube. Same effects work in both formats.
Full REST API with API keys, rate limiting, and scoped permissions. Automate reel generation from your app or n8n workflow.
Deploy on your own VPS with Docker. No vendor lock-in. Your data, your infrastructure, your rules.
Mix and match effects to create professional-looking content without editing software.
Text Cards
Gradient intro/chapter screens
B-Roll Cutaways
5 transition types
Karaoke Captions
Word-by-word highlight
Punch-in Zoom
Spring or smooth easing
Highlight Boxes
Draw attention with glow
Animated Counters
Numbers that count up
Lower Thirds
Name tags and context
CTA Overlays
Buttons and pills
Write a script, hit generate, get a reel. Free tier included.