Skip to main content
skill CX Codex

text-to-speech · benchflow-ai — Claude Code skill for TTS audio mastering

The text-to-speech skill guides TTS cleanup, loudness matching, and segment timing for video audio exports.

Apache-2.0 4 installs ★ 1,933 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add benchflow-ai/skillsbench --skill text-to-speech -a claude-code
Open on GitHub

What text-to-speech does

The skill covers preparing speech clips for delivery: filtering low rumble, optionally softening harsh high frequencies, and adding short fades at clip edges. It uses FFmpeg ebur128 to measure loudness and recommends loudnorm after cleanup and timing edits.

When assembling a track, match each clip to its target time window. Add silence to a short clip; gently adjust or carefully trim a long one, then apply fades at the boundaries. If duration changes after loudness normalization, run normalization again. Otherwise, the final level may no longer match the intended target.

The appropriate target depends on the task. The skill gives -23 LUFS and about -1.5 dBTP as common reference values. Check the generated audio’s native sample rate before resampling. It also outlines choosing between offline, cloud, and formant TTS engines.

What it helps with

  • Remove rumble and clicks from TTS clips
  • Normalize speech loudness before export
  • Fit spoken segments to target time windows
  • Assemble TTS clips into a video track

Example prompts for the agent

  • Clean these TTS clips and match their loudness for a video export.
  • Assemble the speech segments and fit each one to its target window.
  • Recheck loudness after changing the duration of the audio.

How to install text-to-speech

1Skills CLI (Vercel)

npx skills add benchflow-ai/skillsbench --skill text-to-speech -a claude-code

2Manually: put the files in place

~/.claude/skills/text-to-speech/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/text-to-speech/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about text-to-speech

How do I install text-to-speech in Claude Code?

Run npx skills add benchflow-ai/skillsbench --skill text-to-speech -a claude-code. The skill file is at ~/.claude/skills/text-to-speech/SKILL.md.

What does text-to-speech do?

It provides steps for cleaning TTS audio, matching loudness, and aligning speech segments before video delivery.

How should I handle a segment that misses its target duration?

Pad a short clip with silence. For a long one, make a gentle speed adjustment or trim it carefully, then add fades at the boundaries.

Source text

SKILL.md · Apache-2.0
---

name: text-to-speech
description: "Practical mastering steps for TTS audio: cleanup, loudness normalization, alignment, and delivery specs."
---

# 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.

© benchflow-ai · Apache-2.0 · benchflow-ai/skillsbench

Similar skills

All skills for AI and ML →

text-to-speech by other authors comes first.

text-to-speech calesthio text-to-speech is a Claude Code skill that turns text into audio with HeyGen’s Starfish model. It handles voice selection and speech settings. CX Codex +1 1,300installs text-to-speech elevenlabs text-to-speech is a Claude Code skill for generating speech with ElevenLabs. It activates for text-to-audio tasks, voiceovers, and voice app development. CX Codex +1 22,900installs text-to-speech martinholovsky text-to-speech — a skill that walks the agent through Kokoro TTS: building a synthesis engine, streaming audio as it is generated, and clearing the files it writes. CX Codex +1 237installs text-to-speech 101-skills text-to-speech gives the agent ready belt commands for speech synthesis: Kokoro, ElevenLabs, Inworld TTS-2 with emotion steering, and a few more models. CX Codex +1 246installs Text to Speech — 20+ Languages, MP3 Output axel-belfort Text to Speech — 20+ Languages, MP3 Output is a Claude Code MCP server that converts text into speech in 20+ languages and returns base64 MP3 audio for voice alerts and spoken UI. CX Codex +1 2,769installs azure-text-to-speech calesthio azure-text-to-speech synthesizes neural voiceover audio using the Azure AI Speech REST API. Ideal for OpenMontage pipelines that need multilingual narration voices. CX Codex +1 738installs venice-audio-speech veniceai The venice-audio-speech skill covers Venice API text-to-speech and voice cloning. Use it for narration, spoken replies, or audio returned inside an app. CX Codex +1 ★ 176repo stars azure-speech MicrosoftDocs Skill for Claude Code and Codex guides development with Azure Speech in Foundry Tools. Activates during setup of speech-to-text, synthesis, avatars, and Voice Live agent workflows. CX Codex +1 249installs speech-to-text elevenlabs speech-to-text — a Claude Code skill that transcribes audio and video to text using ElevenLabs Scribe v3. Runs when converting media, generating subtitles, or transcribing meetings. CX Codex +1 16,200installs google-cloud-speech calesthio google-cloud-speech is a Claude Code skill for Google Cloud speech workflows, covering transcription, captions, narration, and voice planning. CX Codex +1 132installs

From the same set22

The whole set →
pymatgen pymatgen handles crystal structure transformations, file conversions between CIF and POSCAR, symmetry analysis, and Materials Project queries. CX Codex +1 12installs trend-analysis trend-analysis guides agents in evaluating time series trends using linear regression and Sen's slope. CX Codex +1 8installs threejs This skill maps Three.js scene groups to parts, then prepares per-part OBJ files or URDF links. Use it when a scene needs structured geometry export. CX Codex +1 8installs reflow-machine-maintenance-guidance reflow-machine-maintenance-guidance handles reflow oven upkeep questions by computing ramp rates, time above liquidus and conveyor limits from thermocouple logs, MES data and the handbook. CX Codex +1 5installs civ6lib civ6lib validates Civilization 6 district placement and computes adjacency bonuses. Use it when an agent needs to reason about city layouts and game rules. CX Codex +1 2installs meteorology-driver-classification meteorology-driver-classification sorts the columns of an environmental dataset into heat, flow, wind and human drivers, so an attribution run can treat each group as one factor. CX Codex +1 2installs scipy-curve-fit scipy-curve-fit guides coding agents to estimate nonlinear model parameters from experimental data with scipy.optimize.curve_fit. CX Codex +1 2installs python-scala-idioms python-scala-idioms guides AI agents to translate Python into idiomatic Scala. Enforces immutability, pattern matching, sealed domain traits, and type-safe error handling. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open