Audio Mixing

Combine the TTS speech audio and Lyria background music into a single, polished radio show file.

Embedded Script

python3 skills/audio-mixing/scripts/mix_audio.py --workspace ./workspace

Arguments

Argument	Default	Description
`--workspace`	`workspace`	Root workspace directory

What it does

Loads speech from {workspace}/audio/speech/speech.wav.
Adds 3 seconds of silence padding to the end of the speech to prevent it from being faded out.
Loads background music from {workspace}/audio/music/background.mp3 (if exists).
Loops music to match speech duration, lowers volume to -18dB.
Overlays speech on music with a 1-second music intro.
Adds fade-in/fade-out.
Exports as MP3.

Dependencies

pydub
ffmpeg (system)

Mixing Guidelines

Element	Level	Notes
Speech	0 dB	Untouched, full volume
Background music	-18 dB	Barely audible — subtle bed under speech

Transitions

Music fade-in: 3 seconds
Music fade-out: 5 seconds
Overall fade-in: 500ms
Overall fade-out: 2 seconds

Output

File	Path	Format
MP3 (distribution)	`{workspace}/audio/final/ai_radio.mp3`	MP3, 192kbps

Fallback

If no background music exists, produces speech-only output with just fade-in/fade-out applied.

Files1

1 files · 3.4 KB

Select a file to preview

Overall Score

87/100

Grade

A

Excellent

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

90

Quality

88

Clarity

84

Completeness

82

Summary

This skill mixes speech audio (TTS) and background music into a polished radio show MP3 file. It loads speech from a workspace directory, optionally adds looped background music at -18dB, applies fade transitions, and exports a 192kbps MP3 to a specified output directory. The implementation is straightforward and scoped entirely to a single workspace.

Detected Capabilities

file read (wav, mp3)file write (mp3)audio processing (pydub, ffmpeg)directory creationcommand-line argument parsing

Trigger Keywords

Phrases that agents use to match this skill to user intent.

mix audio trackscombine speech and musicradio show productionaudio post-processingcreate podcast mix

Risk Signals

INFO

No security-relevant patterns detected by static scan

overall

Referenced Domains

External domains referenced in skill content, detected by static analysis.

www.apache.org

Use Cases

Create polished radio show audio by mixing TTS speech with background music
Blend pre-recorded speech with looped background tracks for podcast production
Apply professional fade-in/fade-out and volume balancing to audio projects
Generate speech-only output when background music is unavailable (fallback mode)
Automate audio mixing workflows within a structured workspace directory

Quality Notes

Skill is well-scoped to workspace directory — all input/output paths are relative and documented
Clear mixing guidelines with dB levels and transition timings specified in documentation
Fallback behavior documented: produces speech-only output if music is missing
Error handling for MP3 export includes try-catch with informative error message
Python script includes copyright header and Apache 2.0 license
Usage instructions clear with required dependencies listed
Output statistics provided (file size, duration)
Script uses os.path.join for cross-platform path handling
No hardcoded paths or secrets — all configurable via --workspace argument
Documentation matches implementation — guidelines and actual code align

Model: claude-haiku-4-5-20251001Analyzed: Oct 29, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

audio-mixing