Hermes Registry

Search the registry

One search across every skill, MCP server, agent, and workflow.

7 results

ElevenLabs

1.0.0

ElevenLabs

MCP

Official text-to-speech and audio server — generate speech, clone voices, transcribe. Only clone voices you're allowed to.

creatoraudiotts
0

audiocraft-audio-generation

1.0.0

Orchestra Research · mlops

Skill

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

MultimodalAudio GenerationText-to-Music
0

comfyui

5.1.0

kshitijk4poor,alt-glitch,purzbeats · creative

Skill

Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.

comfyuiimage-generationstable-diffusion
0

heartmula

1.0.0

· media

Skill

HeartMuLa: Suno-like song generation from lyrics + tags.

musicaudiogeneration
0

open-design

1.0.0

nexu-io · design

Skill

Use when you need to generate UI designs, web/mobile mockups, presentations, dashboards, or documents from natural language. 31 composable skills across 129 design systems with image, video, and audio generation.

designuimockup
0

speech

1.0.0

openai · media

Skill

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

SpeechTTSAudio
0

touchdesigner-mcp

1.1.0

kshitijk4poor · creative

Skill

Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

TouchDesignerMCPtwozero
0