← Back to Skills Marketplace
Voice Reply
by
stolot0mt0m
· GitHub ↗
· v1.0.0
4639
Downloads
6
Stars
35
Active Installs
1
Versions
Install in OpenClaw
/install voice-reply
Description
Local text-to-speech using Piper voices via sherpa-onnx. 100% offline, no API keys required.
Use when user asks for a voice reply, audio response, spoken answer, or wants to hear something read aloud.
Supports multiple languages including German (thorsten) and English (ryan) voices.
Outputs Telegram-compatible voice notes with [[audio_as_voice]] tag.
Usage Guidance
Review the installer before running it with sudo, verify the GitHub release artifacts if possible, and confirm the missing `bin/voice-reply` command is present and reviewable in the installed package before relying on the skill.
Capability Analysis
Type: OpenClaw Skill
Name: voice-reply
Version: 1.0.0
The skill is designed for local text-to-speech using sherpa-onnx and Piper voices. The `SKILL.md` and `scripts/install.sh` files contain instructions and commands to download and install necessary binaries and voice models from `https://github.com/k2-fsa/sherpa-onnx/releases/`. While the installation involves `sudo` and `curl` from external sources, these actions are directly aligned with the stated purpose of setting up a local TTS engine and its dependencies. There is no evidence of data exfiltration, malicious execution, persistence, prompt injection attempts against the agent, or other harmful behaviors. The external URLs point to legitimate resources for the project.
Capability Assessment
Purpose & Capability
The stated purpose, README, SKILL.md, and installer consistently describe local TTS using sherpa-onnx and Piper voices, with no API keys, account access, or data exfiltration shown; however, the referenced `{baseDir}/bin/voice-reply` runtime wrapper is not present in the reviewed files.
Instruction Scope
The invocation language is broad for normal voice/audio reply requests, but it is aligned with the skill’s purpose and does not instruct hidden, autonomous, or unrelated behavior.
Install Mechanism
Installation is disclosed and user-directed, but it requires root privileges, apt, curl, and extraction of GitHub release archives without pinned checksums or signatures.
Credentials
Linux, ffmpeg, `/opt` install paths, environment variables for model locations, and temporary audio output are proportionate for an offline TTS tool.
Persistence & Privilege
The installer persists binaries and voice models under `/opt` and runs a downloaded TTS binary during setup, but there is no evidence of background services, autostart, credential use, or ongoing privilege escalation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-reply - After installation, invoke the skill by name or use
/voice-reply - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of voice-reply.
- Generates speech replies locally using Piper TTS via sherpa-onnx; 100% offline, no cloud APIs or API keys required.
- Supports German and English voices, with automatic language detection.
- Produces Telegram-compatible voice notes (voice bubbles) via [[audio_as_voice]] tag.
- Installation instructions provided for sherpa-onnx, Piper models, ffmpeg, and environment setup.
- Easy command-line usage for generating voice replies from text.
Metadata
Frequently Asked Questions
What is Voice Reply?
Local text-to-speech using Piper voices via sherpa-onnx. 100% offline, no API keys required. Use when user asks for a voice reply, audio response, spoken answer, or wants to hear something read aloud. Supports multiple languages including German (thorsten) and English (ryan) voices. Outputs Telegram-compatible voice notes with [[audio_as_voice]] tag. It is an AI Agent Skill for Claude Code / OpenClaw, with 4639 downloads so far.
How do I install Voice Reply?
Run "/install voice-reply" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice Reply free?
Yes, Voice Reply is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Voice Reply support?
Voice Reply is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux).
Who created Voice Reply?
It is built and maintained by stolot0mt0m (@stolot0mt0m); the current version is v1.0.0.
More Skills