Features

Everything you need to go from raw footage to published video.

Transcription, editing, AI generation, and multi-platform export — all driven from the transcript, not a timeline.

Transcription & Captions

Whisper-powered transcription with word-level timing and speaker detection. Edit the transcript and the video follows.

Full control over font, size, weight, color, background, opacity, and position. Clean, karaoke, or emphasis rendering modes.

AI-powered translation to 20+ languages. Show original and translated captions simultaneously with burned-in support.

Export captions as SRT, VTT, plain text, or FCPXML for Final Cut Pro. Burn subtitles directly into MOV or MP4.

Delete words, sentences, or entire blocks from the transcript. VideoBro recompiles the video with smart cuts — no timeline scrubbing.

Configurable noise threshold and minimum duration. Preview silence ranges on the waveform before committing cuts.

Detects hesitations (um, uh, ah) and fillers (like, basically, you know). One-click removal with orange markers on the waveform.

FFmpeg-based scene change detection marks visual boundaries on the timeline for precise content segmentation.

Generate B-roll, thumbnails, and explainer visuals from text prompts using FLUX via fal.ai.

Text-to-speech powered by ElevenLabs. Generate narration, corrected takes, or alternate reads and add them to the timeline.

Describe the mood and get a generated BGM track. Add to the multi-track timeline with per-clip volume control.

Generate sound effects from text descriptions. Layer them precisely on the timeline at any position.

Upload a photo, provide a script, and generate a talking-head video. AI handles lip sync and narration together.

Write a script, pick a voice and style, and VideoBro generates images, TTS, and Ken Burns video for each segment — fully automatic.

Layer BGM, SFX, and voice-over tracks below the waveform. Per-track mute and volume, drag-to-seek, clip positioning.

One-click presets for YouTube Shorts, Instagram Reels, TikTok, LinkedIn, YouTube, and Instagram Feed with aspect ratio and duration rules.

MOV and MP4 export with smart cuts, optional burned-in subtitles, and multi-track audio mixdown — all processed with FFmpeg.

Early access