This is what I'm building, in real time. Priorities shift based on what you tell me. If something here matters to you, let me know.
Cloud-powered word-level speech-to-text with 99+ language support.
Cloud transcription for faster results and longer files — no browser limits.
AI-powered transcription + transliteration pipeline for Hindi-English mixed content.
Drag-and-drop editor with live Remotion preview — style, position, and animate captions frame by frame.
Entrance animations — fade, scale, bounce, glitch, wave, typewriter, scramble, and more.
Flash, Reveal, Pop, and Highlight — each with distinct display behavior and timing.
One-click text looks — Comics, Chrome, Neon, Sticker, Retro Sunset, and more.
Full visual presets combining category, animation, font, colors, and layout in one click.
Client-side video rendering via Remotion — captions burned into the video, download-ready.
Optional upload of media files to cloud storage for safe backup.
Projects saved locally in your browser. Free account required for export.
LLM-powered clip segmentation that understands meaning — keeps phrases together, breaks at punchlines.
Contextual emphasis — AI picks the impactful words instead of keyword matching.
Tuning glow intensity, shadow consistency, and preview accuracy across all style presets.
Sign in with Clerk — sync projects across devices, access from anywhere.
Transcription and UI support for Spanish, French, German, Portuguese, Japanese, and more.
Upload your own .ttf/.otf fonts for brand consistency.
Export captions as subtitle files for YouTube, TikTok, and other platforms.
Queue multiple videos and process them with the same caption style.
AI-suggested stock footage clips matched to transcript content.
Share projects with team members — real-time co-editing.
Touch-optimized editor for captioning directly on phone.
REST API for programmatic caption generation — integrate into your pipeline.