← Back to Skills Marketplace
145
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install voicetrust
Description
Interpret VoiceTrust results for owner verification on voice/audio inputs. Use when you need the meaning of VoiceTrust fields, trust labels, command-gating d...
Usage Guidance
This skill appears to do what it claims: local speaker verification using SpeechBrain models. Before installing/running: 1) Inspect and verify the raw model URLs and the hard-coded SHA-256 checksums in scripts/ensure_models.py (the script will fail if checksums don't match). Prefer obtaining model checkpoints from the official upstream (SpeechBrain / HuggingFace) if you want stronger provenance guarantees. 2) Be aware the runtime will write enrollment/voiceprint files to runtime/data/owners and runtime/data/voiceprints — do not share those files if you want the enrolled identity private. 3) The runtime requires heavy ML deps (torch, speechbrain, etc.) and optionally ffmpeg; expect a large install and CPU/GPU resource use. 4) If you are concerned about network supply-chain risk, run ensure_models.py only after manually auditing the URLs or by populating the assets directory with checkpoints you obtained from an upstream release. Otherwise the skill is internally consistent and proportionate for its stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: voicetrust
Version: 0.4.1
The VoiceTrust skill bundle provides a legitimate implementation for speaker verification and trust scoring using the SpeechBrain framework. It includes well-structured code for managing local voice profiles, processing audio via soundfile or ffmpeg, and providing the AI agent with clear logic for command-gating decisions. Security best practices are observed, such as SHA256 hash verification for model assets downloaded by `scripts/ensure_models.py` and explicit documentation regarding the privacy and local-only storage of biometric enrollment data. No evidence of malicious intent, data exfiltration, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match the implementation: code implements speaker verification, audio quality, and decision gating. Requested dependencies (torch/speechbrain) and local model files are appropriate for a local speaker-verification system. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md limits runtime actions to running STT, running VoiceTrust, and local bootstrap via references/quickstart.md. The included CLI/demo scripts and pipeline operate on local audio files and local owner enrollment state; they do not instruct reading unrelated system files or exfiltrating data. The skill explicitly warns owner enrollment data should remain local.
Install Mechanism
The bundle is instruction-only (no platform install spec), but includes scripts that download large model checkpoint files at runtime from a GitHub raw mirror (raw.githubusercontent.com/ChuaKhunngan/VoiceTrust/...). This is a reasonable approach for model-heavy tools, and the downloader includes hard-coded SHA-256 checks for each file (good). Still, downloading binary checkpoints from a personal mirror has supply-chain risk—users should verify the canonical repo, the raw URLs, and checksums before running downloads. The use of GitHub raw is common, but the mirror is not an official upstream release host (the script documents the SpeechBrain upstream).
Credentials
The skill declares no required environment variables or credentials and operates on local filesystem paths under the skill runtime (assets/, data/). The README mentions resolving FFMPEG_BIN if present, which is a reasonable runtime hint; no unexplained SECRET/TOKEN/PASSWORD requirements are present.
Persistence & Privilege
always is false and the skill does not request persistent platform-level privileges. It stores local owner enrollment and voiceprints under runtime/data/owners and runtime/data/voiceprints (expected for this purpose). It does not modify other skills or system-wide agent config.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voicetrust - After installation, invoke the skill by name or use
/voicetrust - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.4.1
v0.4.1
- added expected SHA256 verification for model downloads
- clarified model provenance and upstream attribution
- documented local biometric data handling and privacy boundaries
No core VoiceTrust runtime logic was changed in this release.
v0.4.0
This update is primarily a publication-readiness pass for ClawHub.
Changes in v0.4.0 are focused on transparency and reviewability, not new behavior:
- repository metadata was aligned to the canonical VoiceTrust repository
- model provenance was clarified in both docs and downloader output
- the downloader now explicitly states that the underlying ECAPA model originates from the upstream SpeechBrain release:
https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb
- ffmpeg handling was documented more clearly for portability and review purposes
No core VoiceTrust verification logic was changed in this release.
This is a packaging / review-friction reduction update for ClawHub publication.
v0.3.0
VoiceTrust is a trust layer for voice messages in OpenClaw.
When a voice message comes in, STT can tell the system what was said. VoiceTrust adds the other half of the picture: who likely said it, and how much that voice should be trusted.
It is built for a simple job:
work with any OpenClaw-compatible STT path
check whether the speaker likely matches the enrolled owner
combine transcript + trust before the agent replies or acts
stop risky voice-command execution when trust is too low
VoiceTrust does not provide STT itself. It is designed to sit alongside whatever STT path OpenClaw is already using, and remain compatible with different OpenClaw transcription setups.
This makes it useful for voice workflows where messages are not just content, but also instructions, control input, or identity-sensitive actions.
Metadata
Frequently Asked Questions
What is VoiceTrust?
Interpret VoiceTrust results for owner verification on voice/audio inputs. Use when you need the meaning of VoiceTrust fields, trust labels, command-gating d... It is an AI Agent Skill for Claude Code / OpenClaw, with 145 downloads so far.
How do I install VoiceTrust?
Run "/install voicetrust" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is VoiceTrust free?
Yes, VoiceTrust is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does VoiceTrust support?
VoiceTrust is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created VoiceTrust?
It is built and maintained by KunyanCAI (@kunyancai); the current version is v0.4.1.
More Skills