Custom Voiceover

The Custom Voiceover feature allows you to bypass the AI text-to-speech generation entirely by uploading your own pre-recorded audio file. This is ideal if you want to narrate the video yourself, use a professional voice actor, or use a specific external audio track.

⚙️ How It Works

Instead of typing a script for the AI to read, you provide the finished audio. Vidrush then analyzes your audio file to generate the subtitles, visual pacing, and B-roll to match your narration.

To use it:

1. Click the (+) Plus Button next to the prompt input field.
2. Select “Custom Voiceover”.
3. Upload your audio file.

📋 Requirements & Limits

To ensure successful processing, your file must meet these criteria:

• File Formats: Supports MP3, WAV, and other standard audio formats.
• Max File Size: 150 MB
• Duration:
  • Minimum: 6 minutes
  • Maximum: 40 minutes

💡 Note on Cloning: Vidrush does not clone your voice from this file for future use. If you want to create an AI voice clone to generate new text-to-speech, you must train it inside ElevenLabs first, make it public/accessible, and then select it in the standard Voice settings. This feature is strictly for uploading a finished audio track for a specific video.