/SKILL.md
# Qwen3-TTS Skill 本地 GPU 加速语音克隆工具,基于 Qwen3-TTS-12Hz-0.6B-Base 模型。支持单条合成和批量生成。 ## 触发条件 - 用户请求使用 `/qwen-tts` 命令 - 用户需要本地 GPU 语音合成/克隆功能 ## 内置音色 | 名称 | 说明 | |------|------| | 寒冰射手 | 游戏角色配音风格 | | 布里茨 | 机器人风格配音 | | 赵信 | 游戏角色配音风格 | ## 使用方法 ### 全局命令(任意目录可用) 安装后可直接使用 `qwen-tts` 命令: ```bash # 列出内置音色 qwen-tts --list-voices # 使用内置音色合成(单条) qwen-tts -v "寒冰射手" -t "你好,这是测试" -o /tmp/output.wav # 使用自定义参考音频 qwen-tts -r /path/to/reference.wav -t "你好,这是测试" -o /tmp/output.wav # 批量生成:从 txt 文件读取(每行一条文本) qwe
npx skillsauth add ipriyanshuuu/qwen3-tts qwen3-ttsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
本地 GPU 加速语音克隆工具,基于 Qwen3-TTS-12Hz-0.6B-Base 模型。支持单条合成和批量生成。
/qwen-tts 命令| 名称 | 说明 | |------|------| | 寒冰射手 | 游戏角色配音风格 | | 布里茨 | 机器人风格配音 | | 赵信 | 游戏角色配音风格 |
安装后可直接使用 qwen-tts 命令:
# 列出内置音色
qwen-tts --list-voices
# 使用内置音色合成(单条)
qwen-tts -v "寒冰射手" -t "你好,这是测试" -o /tmp/output.wav
# 使用自定义参考音频
qwen-tts -r /path/to/reference.wav -t "你好,这是测试" -o /tmp/output.wav
# 批量生成:从 txt 文件读取(每行一条文本)
qwen-tts -v "赵信" -b /path/to/texts.txt -d /tmp/outputs/
# 批量生成:多个文本参数
qwen-tts -v "赵信" --texts "第一句话" "第二句话" "第三句话" -d /tmp/outputs/
# 使用内置音色合成(单条)
python3 tts_cli.py \
--voice "寒冰射手" \
--text "你好,这是测试" \
--out /tmp/output.wav
# 使用自定义参考音频
python3 tts_cli.py \
--ref-audio /path/to/reference.wav \
--text "你好,这是测试" \
--out /tmp/output.wav
# 批量生成:从 txt 文件读取
python3 tts_cli.py \
--voice "赵信" \
--batch-file /path/to/texts.txt \
--out-dir /tmp/outputs/
# 批量生成:多个文本参数
python3 tts_cli.py \
--voice "赵信" \
--texts "第一句话" "第二句话" "第三句话" \
--out-dir /tmp/outputs/
# 列出内置音色
python3 tts_cli.py --list-voices
from qwen3_tts_client import Qwen3TTSClient
client = Qwen3TTSClient()
# 使用内置音色(单条)
client.synthesize(
text="你好,世界!",
voice="寒冰射手",
output_path="/tmp/output.wav"
)
# 使用自定义音频
client.synthesize(
text="你好,世界!",
ref_audio="/path/to/my_voice.wav",
output_path="/tmp/output.wav"
)
# 批量生成(模型只加载一次)
outputs = client.synthesize_batch(
texts=["第一句话", "第二句话", "第三句话"],
voice="赵信",
output_dir="/tmp/outputs/"
)
# 从 txt 文件批量生成
outputs = client.synthesize_from_file(
txt_file="/path/to/texts.txt",
voice="赵信",
output_dir="/tmp/outputs/"
)
批量模式的优势:
前缀_0001.wav, 前缀_0002.wav ...txt 文件格式:
第一行是第一句话
第二行是第二句话
空行会被自动跳过
第四行是第四句话
python3 install.py
hf-mirror.com (自动配置)Qwen/Qwen3-TTS-12Hz-0.6B-Baseffplay /path/to/output.wavtools
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
tools
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.