Why it matters
Profile
Deepfake detection and media safety for agents. Detects AI-generated audio, images, video, and text; traces audio source (ElevenLabs, Resemble, etc.); applies invisible watermarks for provenance tracking; verifies speaker identity (Beta). Powered by Resemble AI. Core principle: never declare media real or fake without a completed detection result.
setup mediumintegration lowinterface voice
Provenance
Signals
Listed in the awesome-hermes-agent README
Sources: 2 / Surfaces: 1
Fast skim
What the upstream surface says
Short excerpt only, so you can decide whether to click out.
An agent skill for deepfake detection and media safety — powered by Resemble AI.
Give any AI agent the ability to detect AI-generated audio, images, and video using Resemble's detection platform.
Works with any agent that supports markdown skills:
Resemble Detect SkillCompatible AgentsInstallWhat It DoesRequirementsPair With the Resemble MCP Server (Recommended)Easiest setup — hosted SSE endpoint (zero install)How It Works
- A Resemble AI API key
- Media files accessible via public HTTPS URLs
- Decision tree — maps user intent to the correct API capability and endpoint
- Complete API reference — every endpoint, parameter, and response schema
- Score interpretation — how to read and present detection confidence scores
- Workflow templates — full forensics, quick checks, and provenance pipelines
- Red flags — anti-patterns the agent should catch in its own reasoning
- Error handling — every status code with cause and resolution