Turn prompts or images into 5–15 second videos with synced audio
Turn your audio into SRT-timed and aligned video clips in seconds
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Free: 25 starter credits. Basic: $19.90/month for 1,000 credits. Standard: $39.90/month for 2,500 credits. Pro: $99.90/month for 7,500 credits. Video costs: 10 credits per second at 480P, 20 at 768P, 35 at 1080P. One-time yearly plans available at $178.80, $358.80, and $838.80 respectively with 30%
Early access: $19 USD
Key features
Text-to-video generation from prompts
Image-to-video with optional end-frame control
Native audio rendering including dialogue, sound effects, and music
Multiple resolution options: 480P, 768P, 1080P
Reference-to-video using multiple input sources
Dialogue support in 11 languages
Adjustable video length from 5 to 15 seconds
Six aspect ratio options for composition
H3 Max Director for iterative scene direction
H3 Max Lip Sync for talking-head generation from photos
On-device transcription using whisper.cpp
Automatic clip alignment to caption timestamps
Exports Final Cut Pro XML sequence
Supports multiple media formats
Generates SRT subtitle files
Asset mismatch detection and warning
Apple Silicon optimized
Natural file ordering by filename
Developer ID-signed and notarized application
What makes it different
Ranked #1 on Design Arena's August 2026 image-to-video rankings with Elo 1,341
Native audio and dialogue rendering in the same pass without separate voice-over work
Sub-3-second model time for 5-second 768P renders
Preserves text and logos with reliable brand rendering across resolutions
Tuned for prompt adherence and visual aesthetics over base model
No manual dragging and trimming of clips required
Transcription happens on-device, never uploaded
Three-step workflow for quick results
Exact frame-accurate alignment of clips to captions
Native macOS application optimized for Apple Silicon