SkillsAdd

smithery/aiskillstore

tts-skill

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

Installation

$ npx skills add smithery/aiskillstore --skill tts-skill
View on skills.sh ↗ Website ↗

Also in this package

Other skills from smithery/aiskillstore · top by installs.

npx skills add smithery/aiskillstore
zod-validation-patterns 0 zig-docs 0 youtrack 0 yaml-authoring 0 workflow-guide 0 when-setting-network-security-use-network-security-setup 0 when-reviewing-pull-request-orchestrate-comprehensive-code-revie 0 when-gathering-requirements-use-interactive-planner 0 when-deploying-cloud-swarm-use-flow-nexus-swarm 0 voice-agent-expert 0

Browse all from smithery/aiskillstore

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,940 B
  • docs SUMMARY.md 130 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

🎙️ TTS-Skill — 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 "测试文本" --voice Lei

Output

If --output is not provided:

  • Output directory: output/
  • Filename pattern: YYYYMMDDHHMMSS<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/
├── .trae/
│   └── plans/
├── assets/
│   ├── Lei.txt
│   ├── 寒冰射手.txt
│   ├── 布里茨.txt
│   └── 赵信.txt
├── engines/
│   ├── edge-tts-cli.py
│   ├── edge-tts.config
│   ├── openai-tts-cli.py
│   ├── openai-tts.config
│   ├── qwen3-tts-cli.py
│   └── qwen3-tts.config
├── input/
│   └── text.txt
├── output/
├── tts-skill.py
├── INSTALL.md
├── INSTALL.zh-CN.md
├── README.md
├── README.zh-CN.md
├── SKILL.md
└── SKILL.zh-CN.md

Chinese Spec

See [SKILL.zh-CN.md](SKILL.zh-CN.md).