| What it does | Convert images and PDFs to editable PowerPoint presentations
| AI lip sync, dubbing and talking video for Claude Code, Codex, Cursor and other agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: 500 signup credits, up to 12 standard image conversions. Everyday Pack (20 Pages): $1.40 for 800 credits (20 standard or 10 high-quality conversions). Professional Pack (100 Pages): $7.00 for 4,000 credits (100 standard or 50 high-quality conversions). Bulk Pack (200 Pages): $14.00 for 8,000 c
| Free tier: 3 free video generations per month (up to 15 seconds each), 10 monthly audio generations. Paid plans on legacy usage billing: Hobbyist ($6 invoice threshold, $0.04-$0.05/sec lipsync-2), Creator ($20 threshold, $0.067-$0.083/sec lipsync-2-pro), Growth ($50 threshold), Scale ($250 threshold
|
|---|
| Key features | - AI-powered text recognition and layer extraction
- Five-layer separation: text, photos, icons, cards, and background
- 3D layer visualization and editing
- Support for PNG, JPG, PDF, and PPTX input formats
- Export to editable PPTX for PowerPoint, Keynote, and Google Slides
- High-quality conversion mode for complex designs
- Image-slide mode to keep original image as single object
- Free local PPTX rebuilding from slides and notes
- Slides & Notes feature to create study materials
- No account required for image-slide mode and basic PPTX creation
| - Lip-sync videos to new audio or typed scripts
- Make photos, portraits and characters talk
- Add dialogue to AI-generated video clips from Veo, Kling, Sora
- Dub videos into other languages with matching lips
- Edit or remove spoken words in original voice
- Localize campaigns across multiple markets
- Batch lip-sync CSV rows or folders resumably
- Build sync. into apps with REST API and SDKs
- Integration with Claude Code, Codex, Cursor and other agents
- Cost estimation and approval before paid work
|
|---|
| What makes it different | - Converts AI-generated slides, screenshots, and images into editable presentations with separated layers
- Intelligently separates content into five distinct layers for granular editing control
- Free local conversion and image-slide mode eliminate upfront costs
- Recognizes and extracts editable text from slide images automatically
- Supports batch conversion of multiple images and PDFs
| - Agent-first approach: works natively with Claude Code, Codex, Cursor and other AI agents
- Plain language commands: describe what you want and the agent picks the matching skill
- Always-approved billing: costs quoted before paid work with user approval required
- Complete end-to-end workflow: from lip-sync to dubbing to localization to API integration
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ▲ +1 (up) since last check | 67 ▲ +1 (up) since last check |
|---|
| Trust Flow (Majestic) | 2 | 12 |
|---|
| Citation Flow (Majestic) | 14 | 42 |
|---|
| Referring domains (Majestic) | 5 | 1145 |
|---|
EditablePPT
sync.