跳到正文
cccskills
免费在 GitHub 公开

text-to-speech

Practical mastering steps for TTS audio: cleanup, loudness normalization, alignment, and delivery specs.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Perform various data analysis on SEC 13-F and obtain some insights of fund activities such as number of holdings, AUM, and change of holdings between two quarters.

中文简介正在准备中。当前显示原文说明。

benchflow-ai/skillsbench18652026年10月13日 更新

AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow.

中文简介正在准备中。当前显示原文说明。

benchflow-ai/skillsbench18652026年10月13日 更新

Redact text from PDF documents for blind review anonymization

中文简介正在准备中。当前显示原文说明。

benchflow-ai/skillsbench18652026年10月13日 更新

Use when checking simplified ADA-derived plan-view bathroom accessibility constraints such as turning space, door clear width, toilet centerline, grab bars, and lavatory knee/toe clearance.

中文简介正在准备中。当前显示原文说明。

benchflow-ai/skillsbench18652026年10月13日 更新

Analyze failed GitHub Action jobs for a pull request.

中文简介正在准备中。当前显示原文说明。

benchflow-ai/skillsbench18652026年10月13日 更新

Use when extracting plan-view architectural geometry from DXF files with semantic CAD layers, especially when outputs must normalize rooms, doors, fixtures, clearances, and grab bars into machine-checkable JSON.

中文简介正在准备中。当前显示原文说明。

benchflow-ai/skillsbench18652026年10月13日 更新

查看 benchflow-ai 的全部技能

报告此技能的问题