Turn your photos into a 15-second AI desk concert with a band and generated music
Free, open-source video captions you control
Stage
Startup
Startup
Founded
2026
2026
Based in
Not given
Not given
Pricing model
Paid
Freemium
Pricing
Single Take: $9.99 for 1 video. Encore Pack: $19.99 for 3 videos. Full Set: $29.99 for 5 videos. One payment, no subscription, unused credits never expire.
Free app (1080p at 30 fps), Pro one-time purchase 14.99 €, self-hosting free
Key features
7 templates with different musical genres and band setups
15-second video output at 720p resolution
Original AI-generated music for each video
Download as MP4 for social media posting
Support for 1 to 5 photos per video
Automatic credit return on failed generations
Personal or group inspiration modes for casting
Video storage in My videos library
No expiration on unused credits
Transcription with Whisper, Parakeet, or Apple Speech
Word-by-word animated captions
Caption styling and correction
Export as MP4, WebM, ProRes, SRT, VTT or JSON
iPhone app with on-device transcription
Self-hosted Docker deployment
HTTP API for scripts and pipelines
Integration with Claude, Cursor and MCP clients
Support for 13 interface languages
GPU acceleration optional for faster transcription
What makes it different
7 distinct templates designed around real example videos
Adults-only tool with privacy protections on photos
Open source with Rust engine shared across browser, app and server
No uploads: iPhone app transcribes on device, self-hosted keeps videos local
Free with one-time Pro purchase, no subscription required
Run on your own server with Docker, no dependency on external services
Agent integration for video captioning from Claude and other AI tools
Tiny Desk AI
OpenCaptions