Connect

Video Voiceover & BGM Mixing

SpaceZephyrbySpaceZephyr
•
954
•
Content Management

Automates video audio production through TTS voiceover generation, copyright-free BGM sourcing, and multi-track ffmpeg mixing with dynamic audio ducking.

Space Video Audio provides an end-to-end audio production pipeline for video creators, combining automated text-to-speech narration, copyright-safe background music curation, and professional ffmpeg-based audio mixing. It supports multiple TTS engines including Edge-TTS and IndexTTS2 voice cloning, automatically matches BGM mood and timing, normalizes loudness to -14 LUFS, and executes dynamic sidechain ducking so dialogue stays clear over background music without re-encoding video streams.

Key Features

01Royalty-free BGM sourcing guidelines and automated downloads via yt-dlp or direct links
02Lossless video packaging with audio fade transitions using stream copying
03Multi-backend TTS voiceover generation using Edge-TTS, IndexTTS2, or system voices
04Broadcast-ready loudness normalization targeting -14 LUFS for online platforms
05954 GitHub stars
06Automated dynamic audio ducking using ffmpeg sidechain compression

Use Cases

01Normalizing and mastering final audio tracks without re-encoding existing video frames
02Adding mood-appropriate BGM with automated volume ducking to tutorial or marketing videos
03Generating spoken narration from script files and aligning it with background music