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.zipInstalls 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.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
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:
- Measure loudness using FFmpeg
ebur128(or equivalent meter). - Apply normalization (e.g.,
loudnorm) as the final step after cleanup and timing edits. - 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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| tts-audio-mastering (this skill) | 1 | 2mo | No flags | Intermediate |
| youtube-transcript | 68 | 9mo | Review | Intermediate |
| docx | 93 | 5mo | Review | Advanced |
| openai-whisper | 38 | 2mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by benchflow-ai
View all by benchflow-ai →You might also like
youtube-transcript
michalparkola
Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.
docx
anthropics
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
openai-whisper
openclaw
Local speech-to-text with the Whisper CLI (no API key).
braindump
huytieu
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
prompt-library
davila7
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
hr-pro
sickn33
Professional, ethical HR partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee relations. Ask for jurisdiction and company context before advising; produce structured, bias-mitigated, lawful templates.