Features
Text-to-video generation with text prompts
Realistic human generation with facial consistency
Built-in optional sound generation
Camera control: fixed or dynamic modes
Resolution options: 480p and 720p
Duration control: 4–15 seconds
Aspect ratios: 21:9, 16:9, 9:16, 1:1, 4:3, 3:4
Asynchronous task submission with polling
REST API with JSON interface
Code examples in JavaScript, Python, cURL
Free playground for testing
Unified billing across Flaq AI models
Dual-Branch Diffusion Transformer architecture
Seedance 2.5 and 2.0 Mini available as alternatives
Image-to-video generation also supported
Automatic on-screen text detection
Text erasure and visual rebuilding in target language
Context-aware translation engine
Editable translations with full control
Side-by-side original vs translated comparison view
Flexible text styling (font, size, color)
No original project files required
Slide-based video text localization
Training video text translation (instructions, labels, warnings)
Product promo text translation (feature highlights, callouts)
Proofread before export with built-in editor
Integrated with Vozo subtitles, dubbing, and lip-sync
Supports 111 source & 165 target languages
Glossary and brand governance (Studio+ plans)
Bulk upload (Studio+ plans)
