Script-first recording studio for talking videos on your phone
AI video generator creating cinematic videos with synchronized sound from text or images
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free version with core features. Pro: $9.99 per month, $49.99 per year with 3-day free trial, or $129.99 one-time lifetime purchase.
Basic $19.90/month ($9.90/month billed annually at $118.80); Standard $39.90/month ($19.90/month billed annually at $238.80); Pro $99.90/month ($49.90/month billed annually at $598.80). Basic includes 560 credits/month, Standard includes 1,800 credits/month, Pro includes 5,400 credits/month. All pla
Key features
Auto-scrolling teleprompter with customizable reading speed (80-360 words per minute)
On-device speech transcription and captions with 15 styles
Automatic silence and filler detection
Recording with background music playback
Timeline editing with transitions and clip animations
Background blur or replacement via on-device segmentation
Project saving and resumption
Full Arabic language support with right-to-left layout
Watermark customization
AI script generation
Text to video generation from text prompts
Image to video animation
Native synchronized audio and sound generation
Up to 4K resolution output
8+ language phoneme-level lip sync
Up to 30 reference images for creative control
Up to 30 seconds video duration
Six aspect ratio options
Multi-shot storytelling with natural transitions
Average generation time under 8 minutes
What makes it different
Entire workflow stays on your phone with no upload or account required
Script-first approach: write or generate before recording
On-device captions and cleanup work offline after model download
Full interface available in English and Arabic with RTL support
Background continues playing during recording without interruption
Native audio-video joint generation creates synchronized sound in one pass without separate audio tools
Multimodal reference system with up to 30 images for consistent character and style control
8-language phoneme-level lip sync with frame-accurate synchronization
Powered by ByteDance's advanced Seedance 2.0 model
Cinema-grade specs including up to 4K output and advanced physics rendering