← 返回 Skills 市场
Outil
Kittentts
作者
Fred Ghilini
· GitHub ↗
· v1.0.0
· MIT-0
30
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install kittentts
功能描述
Generate local TTS audio using the KittenTTS model with selectable voices and multiple model sizes for balance of quality and speed.
使用说明 (SKILL.md)
KittenTTS Skill
Génère des réponses audio TTS localement avec le modèle KittenTTS.
Installation
pip install https://github.com/KittenML/KittenTTS/releases/download/0.8.1/kittentts-0.8.1-py3-none-any.whl soundfile
Utilisation
from kittentts import KittenTTS
# Charger le modèle (nano = plus léger, mini = meilleure qualité)
model = KittenTTS("KittenML/kitten-tts-nano-0.8-int8")
# Générer audio
audio = model.generate("Bonjour Fred !", voice="Bella")
# Sauvegarder
model.generate_to_file("Bonjour Fred !", "output.wav", voice="Luna")
Voix disponibles
- Luna (défaut)
- Bella
- Jasper
- Luna
- Bruno
- Rosie
- Hugo
- Kiki
- Leo
Modèles
| Modèle | Paramètres | Taille |
|---|---|---|
| nano-int8 | 15M | 25 MB |
| nano | 15M | 56 MB |
| micro | 40M | 41 MB |
| mini | 80M | 80 MB |
Outil kittentts
Un wrapper CLI est disponible à la racine du workspace :
python kittentts_cli.py "Ton texte ici" --voice Luna --output audio.wav
Note: Le venv se trouve dans skills/kittentts/.venv/
Intégration OpenClaw
Pour utiliser avec l'outil tts d'OpenClaw, le skill génère le fichier audio et le tool tts l'envoie automatiquement sur Telegram.
安全使用建议
Install only if you are comfortable with generated speech audio being sent through Telegram. Do not use it for confidential text unless you have checked the skill's configuration and know exactly which Telegram account or chat receives the audio.
能力评估
Purpose & Capability
The reported behavior of sending generated audio through Telegram is coherent with a TTS or messaging integration, but it can expose whatever text was converted to speech.
Instruction Scope
SkillSpector flagged that the Telegram forwarding behavior is documented but may not be framed as an explicit consent boundary; this is a disclosure-quality issue rather than evidence of deception.
Install Mechanism
No artifact-backed evidence was provided or found showing a deceptive installer, hidden package install, or unrelated setup behavior.
Credentials
Network transfer to Telegram is proportionate for a Telegram audio workflow, but users should avoid synthesizing sensitive text unless they intend the resulting audio to be sent externally.
Persistence & Privilege
No evidence indicates persistence, privilege escalation, credential theft, broad local indexing, or background execution beyond the stated integration behavior.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install kittentts - 安装完成后，直接呼叫该 Skill 的名称或使用
/kittentts触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of KittenTTS Skill:
- Generates local TTS audio responses using the KittenTTS model.
- Provides Python and CLI usage instructions.
- Supports multiple voice options (e.g., Luna, Bella, Jasper).
- Offers several model sizes for different quality/performance needs.
- Integrates with OpenClaw for Telegram audio output.
元数据
常见问题
Kittentts 是什么？
Generate local TTS audio using the KittenTTS model with selectable voices and multiple model sizes for balance of quality and speed. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 30 次。
如何安装 Kittentts？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kittentts」即可一键安装，无需额外配置。
Kittentts 是免费的吗？
是的，Kittentts 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Kittentts 支持哪些平台？
Kittentts 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Kittentts？
由 Fred Ghilini（@fredguile）开发并维护，当前版本 v1.0.0。
推荐 Skills