agentsclimarketplace
Sign in

Tts skill

Skill aiskillstore/marketplace/skills/tabortao/tts-skill

Multi-engine text-to-speech skill. Supports Qwen3-TTS local voice cloning, VoiceCraft online TTS, and OpenAI TTS.From its SKILL.md

Install
npx -y skills add aiskillstore/marketplace --skill tts-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

SKILL.md

2.9 KB, 802 tokens by cl100k_base, as published. Nobody here has run it

πŸŽ™οΈ TTS-Skill β€” Multi-Engine Text-to-Speech

TTS-Skill provides a single entrypoint for generating speech using multiple backends, with consistent output naming and progress feedback for long-running jobs.

Engines

  • qwen3-tts: local voice cloning with a reference audio + transcript
  • edge-tts: online voices with speed/pitch/style controls
  • openai-tts: OpenAI speech generation via API

Command Syntax

/tts-skill [engine] [text] --voice [voice-keyword] [other options]

If you use the Python entrypoint:

python tts-skill.py [engine] [text] --voice [voice-keyword]

Text Input

Pass text as a positional argument, or use --text-file / -f to read from a file.

Example:

python tts-skill.py qwen3-tts --text-file "input\\text.txt" --voice 寒冰射手

Notes:

  • --text-file supports relative and absolute paths; relative paths are resolved from your current working directory
  • If both positional text and --text-file are provided, --text-file takes priority
  • UTF-8 is recommended (UTF-8 BOM is supported); on decode error it falls back to GBK

You can also call engine scripts directly:

python engines/qwen3-tts-cli.py --text-file "input\\text.txt" --voice 寒冰射手
python engines/edge-tts-cli.py --text-file "input\\text.txt" --voice xiaoxiao
python engines/openai-tts-cli.py --text-file "input\\text.txt" --voice alloy

Local Voice Assets (Qwen3-TTS)

To add a clone voice, put a matching pair of files in assets/:

assets/Lei.wav
assets/Lei.txt

Supported audio formats: .wav, .mp3, .m4a, .flac.

Then:

python tts-skill.py qwen3-tts "ζ΅‹θ―•ζ–‡ζœ¬" --voice Lei

Output

If --output is not provided:

  • Output directory: output/
  • Filename pattern: YYYYMMDD_HHMMSS_<first-6-chars>.<ext>

Progress & Timing (Qwen3-TTS)

Qwen3-TTS jobs print a live progress bar with ETA. After completion, tts-skill.py prints:

  • total runtime
  • total chars and Chinese chars
  • average seconds per Chinese character (or per char if no Chinese)

Project Layout

tts-skill/
β”œβ”€β”€ .trae/
β”‚   └── plans/
β”œβ”€β”€ assets/
β”‚   β”œβ”€β”€ Lei.txt
β”‚   β”œβ”€β”€ 寒冰射手.txt
β”‚   β”œβ”€β”€ εΈƒι‡ŒθŒ¨.txt
β”‚   └── θ΅΅δΏ‘.txt
β”œβ”€β”€ engines/
β”‚   β”œβ”€β”€ edge-tts-cli.py
β”‚   β”œβ”€β”€ edge-tts.config
β”‚   β”œβ”€β”€ openai-tts-cli.py
β”‚   β”œβ”€β”€ openai-tts.config
β”‚   β”œβ”€β”€ qwen3-tts-cli.py
β”‚   └── qwen3-tts.config
β”œβ”€β”€ input/
β”‚   └── text.txt
β”œβ”€β”€ output/
β”œβ”€β”€ tts-skill.py
β”œβ”€β”€ INSTALL.md
β”œβ”€β”€ INSTALL.zh-CN.md
β”œβ”€β”€ README.md
β”œβ”€β”€ README.zh-CN.md
β”œβ”€β”€ SKILL.md
└── SKILL.zh-CN.md

Chinese Spec

See SKILL.zh-CN.md.

What ships with it: 19 files

206.8 KB alongside SKILL.md, 4 of them executable

assets/

docs/

engines/

input/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.