← 返回 Skills 市场
Piper TTS
作者
bewareofddog
· GitHub ↗
· v1.0.1
843
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install beware-piper-tts
功能描述
Local text-to-speech using Piper for voice message delivery. Use when the user asks for voice responses, audio messages, TTS, text-to-speech, voice notes, or...
使用说明 (SKILL.md)
Piper TTS — Local Voice Messages
Generate voice messages using Piper, a fast local TTS engine. Zero cloud calls, zero cost, zero API keys.
Setup
If Piper is not installed, run the setup script:
scripts/setup-piper.sh
This installs piper-tts via pip and downloads a default voice (en_US-kusal-medium).
Generating Voice Messages
Use scripts/piper-speak.sh to generate and deliver voice:
scripts/piper-speak.sh "\x3Ctext>" [voice]
text: The text to speak (required)voice: Piper voice name (default:en_US-kusal-medium)
The script outputs an MP3 path. Include it in your reply as:
[[audio_as_voice]]
MEDIA:\x3Cpath-to-mp3>
This delivers the audio as a native voice message on supported channels (Telegram, Discord, etc.).
Example Workflow
- User asks: "Tell me a joke as audio"
- Run:
scripts/piper-speak.sh "Why do programmers prefer dark mode? Because light attracts bugs!" - Get MP3 path from output
- Reply with
[[audio_as_voice]]+MEDIA:\x3Cpath>
Available Voices
After setup, download additional voices:
scripts/setup-piper.sh --voice en_US-ryan-high
scripts/setup-piper.sh --voice en_GB-northern_english_male-medium
Popular voices:
en_US-kusal-medium— Clear male voice (default, recommended)en_US-ryan-high— High quality US maleen_US-hfc_male-medium— US maleen_GB-northern_english_male-medium— British male- Browse all: https://huggingface.co/rhasspy/piper-voices
Important Notes
- Speed: Local generation is ~0.5-1s. Much faster than cloud TTS.
- No API keys: Works completely offline after setup.
- Platform: macOS (Apple Silicon + Intel), Linux. Requires Python 3.9+.
- Do NOT set
messages.tts.auto: "always"in OpenClaw config — it makes every response slow. Keep TTS on-demand.
安全使用建议
This skill appears to do what it says: local TTS using Piper and downloaded voice models from HuggingFace. Before running setup-piper.sh, consider: 1) the setup script will run pip3 install (piper-tts) and may run sudo apt-get install ffmpeg — run these commands in a virtualenv or on a machine where you trust installing packages. 2) the voice files are downloaded from https://huggingface.co/rhasspy/piper-voices which is the expected source, but downloads and pip installs execute remote code — review or run in an isolated environment if you have concerns. 3) voices are written to ~/ .local/share/piper-voices (or PIPER_VOICES_DIR if set); no secrets are requested. If you want minimal risk, run setup manually and inspect outputs before enabling the skill.
功能分析
Type: OpenClaw Skill
Name: beware-piper-tts
Version: 1.0.1
The skill is classified as suspicious due to a critical path traversal vulnerability found in `scripts/setup-piper.sh`. The `download_voice` function constructs the output filename (`onnx_file`) directly from the user-controlled `--voice` argument without proper sanitization. This allows an attacker to specify a voice name like `../../.ssh/id_rsa` to write a downloaded file from HuggingFace to an arbitrary location on the filesystem, potentially leading to arbitrary file write or remote code execution if combined with other vulnerabilities or specific file types. While the overall intent of the skill is benign (local TTS), this vulnerability poses a significant security risk.
能力评估
Purpose & Capability
The name/description (local Piper TTS) match the included scripts and README: setup installs piper-tts and downloads voice ONNX files; speak script generates WAV via python -m piper and converts to MP3. No unrelated capabilities or credentials are requested.
Instruction Scope
SKILL.md and scripts keep to TTS: they read PIPER_VOICES_DIR, HOME and TMPDIR (reasonable), call python3 -m piper, ffmpeg, and output an MP3 path. They do not read unrelated system files or send data to unexpected endpoints; voice downloads go to HuggingFace repo.
Install Mechanism
There is no formal install spec (instruction-only). setup-piper.sh installs piper-tts via pip and may install ffmpeg via brew or apt-get (sudo). It downloads model files with curl from huggingface.co (official repo). This is expected but carries normal risks of executing pip/apt and downloading binaries; running in a controlled environment is recommended.
Credentials
The skill requests no credentials or secret env vars. It optionally respects PIPER_VOICES_DIR and TMPDIR (standard local config). No excessive or unrelated environment access is requested.
Persistence & Privilege
always:false and model invocation is normal. The scripts install tools/packages but do not modify other skills or system agent configs. The only elevated action is apt-get which may require sudo during setup — expected for installing ffmpeg on Linux.
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 beware-piper-tts - 安装完成后，直接呼叫该 Skill 的名称或使用
/beware-piper-tts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
v1.0.1
No code or documentation changes detected.
- Version bump only; no functional or content updates in this release.
v1.0.0
Initial release of Piper TTS skill for local text-to-speech.
- Delivers voice messages using the fast, local Piper TTS engine.
- No cloud APIs, no cost, no latency—runs entirely offline.
- Easy setup script for installing Piper and downloading default/enhanced voices.
- Provides scripts to convert text to MP3 voice messages for platforms like Telegram and Discord.
- Supports user requests for voice responses, audio messages, and text-to-speech.
- Includes instructions for adding new voices and example workflow.
元数据
常见问题
Piper TTS 是什么？
Local text-to-speech using Piper for voice message delivery. Use when the user asks for voice responses, audio messages, TTS, text-to-speech, voice notes, or... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 843 次。
如何安装 Piper TTS？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install beware-piper-tts」即可一键安装，无需额外配置。
Piper TTS 是免费的吗？
是的，Piper TTS 完全免费（开源免费），可自由下载、安装和使用。
Piper TTS 支持哪些平台？
Piper TTS 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 Piper TTS？
由 bewareofddog（@bewareofddog）开发并维护，当前版本 v1.0.1。
推荐 Skills