How AI Voice Over Works
Upload any video, then speak your narration while it plays. Your browser converts your speech to text in real time, recording exactly when each sentence was spoken. Edit any segment's text to fix mistakes. When you stop, every segment is sent to Kokoro TTS for natural AI voice generation. Captions are automatically burned into the exported video at the correct timestamps.
Step by Step
- Upload — Drop or browse for your video file (MP4, WebM, MOV).
- Record — Click Start Voice Over. The video plays and your mic captures narration.
- Edit — Click any segment text to fix speech recognition mistakes. Hit Regen to update the AI voice.
- Export — Download the final video with AI narration, captions, and adjustable original audio.
Use Cases
- Add professional narration to tutorial and explainer videos
- Create voice-overs for social media content and ads
- Dub videos with consistent AI voices for branding
- Add captions/subtitles to videos automatically
- Narrate gameplay, product demos, or presentations
Privacy
Your video never leaves your device — all video processing happens locally in your browser. Only the transcribed text is sent to Kokoro TTS for voice generation. No video or microphone audio is uploaded to any server.