TT

tts-audio-mastering

Practical tools and instructions for cleaning and normalizing text-to-speech audio files.

Install

mkdir -p .claude/skills/tts-audio-mastering && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5768" && unzip -o skill.zip -d .claude/skills/tts-audio-mastering && rm skill.zip

Installs to .claude/skills/tts-audio-mastering

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Practical mastering steps for TTS audio: cleanup, loudness normalization, alignment, and delivery specs.
104 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Remove rumble using high-pass filters
  • Normalize loudness to -23 LUFS
  • Apply fade-in/out to segment boundaries
  • Resample audio to match delivery specs
  • Measure integrated loudness

How it works

The skill applies a sequence of signal processing steps including high-pass filtering, loudness normalization, and boundary fading to ensure consistency.

Inputs & outputs

You give it
Raw TTS audio file
You get back
Mastered, delivery-ready audio

When to use tts-audio-mastering

  • Normalize audio loudness for TTS output
  • Clean up artifacts from generated voice clips
  • Prepare audio files for production delivery

About this skill

SKILL: TTS Audio Mastering

This skill focuses on producing clean, consistent, and delivery-ready TTS audio for video tasks. It covers speech cleanup, loudness normalization, segment boundaries, and export specs.

1. TTS Engine & Output Basics

Choose a TTS engine based on deployment constraints and quality needs:

  • Neural offline (e.g., Kokoro): stable, high quality, no network dependency.
  • Cloud TTS (e.g., Edge-TTS / OpenAI TTS): convenient, higher naturalness but network-dependent.
  • Formant TTS (e.g., espeak-ng): for prototyping only; often less natural.

Key rule: Always confirm the native sample rate of the generated audio before resampling for video delivery.


2. Speech Cleanup (Per Segment)

Apply lightweight processing to avoid common artifacts:

  • Rumble/DC removal: high-pass filter around 20 Hz
  • Harshness control: optional low-pass around 16 kHz (helps remove digital fizz)
  • Click/pop prevention: short fades at boundaries (e.g., 50 ms fade-in and fade-out)

Recommended FFmpeg pattern (example):

  • Add filters in a single chain, and keep them consistent across segments.

3. Loudness Normalization

Target loudness depends on the benchmark/task spec. A common target is ITU-R BS.1770 loudness measurement:

  • Integrated loudness: -23 LUFS
  • True peak: around -1.5 dBTP
  • LRA: around 11 (optional)

Recommended workflow:

  1. Measure loudness using FFmpeg ebur128 (or equivalent meter).
  2. Apply normalization (e.g., loudnorm) as the final step after cleanup and timing edits.
  3. If you adjust tempo/duration after normalization, re-normalize again.

4. Timing & Segment Boundary Handling

When stitching segment-level TTS into a full track:

  • Match each segment to its target window as closely as possible.
  • If a segment is shorter than its window, pad with silence.
  • If a segment is longer, use gentle duration control (small speed change) or truncate carefully.
  • Always apply boundary fades after padding/trimming to avoid clicks.

Sync guideline: keep end-to-end drift small (e.g., <= 0.2s) unless the task states otherwise.

When not to use it

  • Processing non-TTS audio sources
  • Applying heavy compression to voice

Limitations

  • Requires consistent sample rate verification
  • Normalization must be re-applied after tempo changes

How it compares

It provides a standardized mastering workflow specifically for TTS, whereas manual editing often lacks consistent loudness and artifact removal.

Compared to similar skills

tts-audio-mastering side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
tts-audio-mastering (this skill)12moNo flagsIntermediate
youtube-transcript689moReviewIntermediate
docx935moReviewAdvanced
openai-whisper382moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry