← Back to Skills Marketplace
919
Downloads
4
Stars
3
Active Installs
10
Versions
Install in OpenClaw
/install webchat-voice-full-stack
Description
One-step full-stack installer for OpenClaw WebChat voice input with local speech-to-text. Orchestrates three focused skills in order: local STT backend (fast...
Usage Guidance
This meta-skill appears to do what it says, but it is a coordinator: its security ultimately depends on the three sub-skill deploy scripts it runs. Before deploying: 1) inspect the sub-skill scripts under $WORKSPACE/skills (especially anything that creates services, writes to gateway config, or touches Control UI); 2) run bash scripts/rehash.sh only after you have manually audited those scripts so checksums.sha256 records a trusted baseline (deploy aborts if no checksum file or mismatches are found); 3) back up your gateway/Control UI configuration so you can restore allowedOrigins and remove any injected script; 4) confirm where the STT model will be downloaded from and ensure you have the bandwidth and trust in that host; 5) ensure WORKSPACE and SKILLS_DIR are not pointing at sensitive system locations (no root/sudo is required, but user-scoped changes will be made). Following these steps will minimize the risk of inadvertently running unreviewed code.
Capability Analysis
Type: OpenClaw Skill
Name: webchat-voice-full-stack
Version: 0.4.1
The skill is a meta-installer designed to orchestrate the deployment of three sub-skills for local speech-to-text and voice UI. It demonstrates a security-conscious design by implementing a mandatory SHA256 integrity verification mechanism in `scripts/deploy.sh`, which validates sub-skill scripts against a checksum file before execution. All documented behaviors, such as creating systemd user services and modifying gateway allowed origins, are transparently disclosed and directly support the stated purpose of providing a local, private voice interface.
Capability Assessment
Purpose & Capability
The skill is a meta-installer whose actions (creating user-level systemd services, injecting a UI script, adding a gateway origin, downloading a local STT model) match the description. It does not request unrelated credentials or binaries. The requirement for Python, GStreamer, and an initial Internet connection for model download is consistent with a local STT deployment.
Instruction Scope
Runtime instructions stay within the stated scope: verify integrity, ensure sub-skills are present, and invoke their deploy scripts. All filesystem and service changes referenced (user systemd services, Control UI script injection, gateway.allowedOrigins) are relevant to enabling voice input. Important caveat: this meta-skill delegates all substantive work to the sub-skills' deploy scripts, so security depends heavily on those scripts; the meta-skill enforces checksum verification but requires the user to generate or commit the trusted baseline before deployment.
Install Mechanism
There is no network-based install spec in this package; it is instruction/script-based and runs local shell scripts. The only network action mentioned is the model download performed by the STT sub-skill on first run (~1.5 GB). No downloads from arbitrary URLs or extraction logic are present in the meta-skill itself.
Credentials
The skill requires no credentials or environment secrets. It uses configurable WORKSPACE and SKILLS_DIR paths and optional VOICE_* env overrides; those are reasonable. One operational note: if SKILLS_DIR/WORKSPACE are redirected to sensitive locations (symlinks, shared system dirs), the scripts will act there — verify these paths before running.
Persistence & Privilege
Persistence is limited to user-scoped systemd services and a single UI injection/allowed-origin change described in the docs. always:false and default autonomous invocation are set. The changes are reversible via uninstall instructions. Updating gateway.allowedOrigins and injecting a script are privileged changes to the local Control UI — expected for this feature but should be reviewed and backed up before applying.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install webchat-voice-full-stack - After installation, invoke the skill by name or use
/webchat-voice-full-stack - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.4.1
MIT license added and full-stack skill republished with explicit repository license.
v0.4.0
Added SHA256 integrity verification for all sub-skill scripts before deployment. Deploy aborts on checksum mismatch. Added rehash.sh for updating trusted baseline after audit. Added VERIFY_ONLY dry-run mode.
v0.3.0
Migrate to 3-skill architecture (faster-whisper-local-service + webchat-https-proxy + webchat-voice-gui), improved security posture wording and docs
v0.2.1
Refresh tags for discoverability (full-stack voice + local STT + webchat).
v0.2.0
Updated description: PTT, Toggle mode, keyboard shortcuts, i18n (en/de/zh), interactive language selection during install
v0.1.4
Fixed hardcoded paths (now configurable via WORKSPACE/SKILLS_DIR env). Removed misleading 'fully offline' claim. Added full transparency: documents all downstream changes from both sub-skills. Added prerequisites, uninstall instructions, clear error messages when sub-skills are missing.
v0.1.3
Improved discoverability: expanded description with voice input, STT, microphone, full stack keywords
v0.1.2
Ranking tune: stronger OpenClaw/WebChat/full-stack/local/no-API naming and tags.
v0.1.1
Searchability update: explicit OpenClaw/WebChat/local voice/no additional API cost wording.
v0.1.0
Initial meta-skill: orchestrates faster-whisper-local-service + webchat-voice-proxy deploy and status checks.
Metadata
Frequently Asked Questions
What is WebChat Voice Full Stack?
One-step full-stack installer for OpenClaw WebChat voice input with local speech-to-text. Orchestrates three focused skills in order: local STT backend (fast... It is an AI Agent Skill for Claude Code / OpenClaw, with 919 downloads so far.
How do I install WebChat Voice Full Stack?
Run "/install webchat-voice-full-stack" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is WebChat Voice Full Stack free?
Yes, WebChat Voice Full Stack is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does WebChat Voice Full Stack support?
WebChat Voice Full Stack is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created WebChat Voice Full Stack?
It is built and maintained by neldar (@neldar); the current version is v0.4.1.
More Skills