agentleFS
zth9zth9/skills/text-to-audio/SKILL.md

text-to-audio

Skill2 starsChanged 10 months agoMITView on GitHub

Convert text to natural speech using ChatTTS local AI model. Use when user wants to generate audio/speech from text, create voice content, or needs high-quality Chinese/English text-to-speech synthesis.

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. shubhomoydas/claude_skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

Files
SKILL.md

Text to Audio

Convert text to natural speech using ChatTTS, a generative speech model designed for conversational scenarios.

Features

  • Local AI model inference (no cloud API required)
  • Natural conversational speech style
  • Chinese and English support
  • Prosody control: laughter, pauses, oral style via prompt tokens
  • Reproducible speaker voice via seed
  • WAV output (24kHz), optional MP3 conversion (requires ffmpeg)

Usage

The agent should use this skill when:

  • User wants to convert text to speech/audio
  • User wants to generate natural-sounding voice content
  • User needs Chinese or English TTS with conversational style

Prerequisites

# Install uv (Python package manager)
brew install uv

# Optional: Install ffmpeg for MP3 output
brew install ffmpeg

Quick Start

1. Install Dependencies (first time)

python scripts/wrapper.py --install

2. Simple Text-to-Speech

python scripts/wrapper.py --text "你好,这是一个测试。" --output output.wav

3. Specify Speaker Seed

python scripts/wrapper.py --text "Hello world" --seed 42 --output output.wav

4. MP3 Output

python scripts/wrapper.py --text "测试MP3输出" --output output.mp3 --format mp3

5. Prosody Control

python scripts/wrapper.py --text "这真是太有趣了" --prompt "[oral_2][laugh_0][break_6]" --output output.wav

CLI Parameters

ParameterShortDefaultDescription
--text-t-Text to convert to speech
--output-o-Output file path (.wav or .mp3)
--seed-srandomSpeaker seed for reproducible voice
--temperature-0.3Temperature for sampling
--top-p-0.7Top-P decoding parameter
--top-k-20Top-K decoding parameter
--prompt-[oral_2][laugh_0][break_6]Prosody prompt tokens
--format-wavOutput format: wav or mp3
--install--Install dependencies only

Prosody Prompt Tokens

ChatTTS supports special tokens to control speech style:

  • [oral_0] to [oral_9] — Oral/casual speech level
  • [laugh_0] to [laugh_9] — Laughter intensity
  • [break_0] to [break_9] — Pause/break duration

Example: [oral_2][laugh_0][break_6] produces natural speech with moderate oral style and longer pauses.

Output

Audio files are saved to the specified --output path. Default format is WAV (24kHz). Use --format mp3 for MP3 output (requires ffmpeg).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.