inference.sh
Official@inference-sh
A comprehensive registry providing modular interface components and cloud-hosted model execution for media generation, content strategy, and digital asset production.
Agent Skills by inference.sh
Showing 83 vetted skills indexed across 1 GitHub repositories.
inference-shp-video-avatar
Generate talking head avatar videos from portrait images using Pruna P-Video-Avatar via the inference.sh CLI.
inference-shhappyhorse
Generate and edit videos with Alibaba HappyHorse 1.0 models via the inference.sh CLI.
inference-shseedance
Generate videos with synchronized audio using ByteDance Seedance 2.0 via the inference.sh CLI.
inference-shgpt-image
Generate and edit images with OpenAI GPT-Image-2 via the inference.sh CLI.
inference-shelevenlabs-sound-effects
Generate AI sound effects from text descriptions via the ElevenLabs API and inference.sh CLI.
inference-shelevenlabs-music
Generates original music from text prompts via the ElevenLabs API through the inference.sh CLI.
inference-shelevenlabs-tts
Generate speech audio from text using ElevenLabs voices via the inference.sh CLI.
inference-shelevenlabs-voice-isolator
Removes background noise and isolates vocals from audio files via the inference.sh CLI.
inference-shelevenlabs-dialogue
Generate multi-speaker dialogue audio with ElevenLabs voices via the inference.sh CLI.
inference-shbuilding-inferencesh-apps
Build, test, and deploy Python or Node.js applications on the inference.sh platform.
inference-shai-podcast
Generates multi-speaker talking head podcast videos via portrait, TTS, avatar, and merge pipeline.
inference-shaffirmations
Resets agent trajectory when stuck in loops, repeated failures, or thrashing during debugging.
inference-shtools-ui
Render React/Next.js UI components for AI agent tool lifecycle management.
inference-shchat-ui
Provide React and Next.js chat UI components with Tailwind CSS.
inference-shwidgets-ui
Render declarative UI components from JSON schemas for React and Next.js.
inference-shagent-ui
Provide a React component for AI agent interfaces with tool execution and streaming.
inference-shinfsh-cli
Execute over 150 cloud-hosted AI applications via a command-line interface.
inference-shagent-tools
Run over 150 cloud-hosted AI applications via a command-line interface.
inference-shimage-to-video
Convert still images into animated videos using AI models via inference.sh CLI.
inference-shgoogle-veo
Generate videos from text prompts using Google Veo models via inference.sh CLI.
inference-shp-video
Generate videos from text or images using Pruna models via inference.sh CLI.
inference-shai-avatar-video
Generates AI avatar and talking head videos via the inference.sh CLI.
inference-shremotion-render
Render videos from React/Remotion component code via the inference.sh CLI.
inference-shai-video-generation
Generate videos from text or image inputs using models like Veo and Wan.
Frequently Asked Questions About inference.sh
FAQPage SchemaWhat specific media generation tasks are supported?▼
The platform enables text-to-video synthesis, AI avatar production, speech-to-text transcription, voice cloning, and high-resolution image generation using models like Veo, FLUX, and Whisper.
Which technical personas benefit from these capabilities?▼
Frontend engineers, creative technologists, and content strategists utilize these components and interfaces to integrate generative media and structured content production into their existing web environments.
How are these models and components accessed?▼
Users interact with the registry via a dedicated interface for model execution, or by integrating React/Next.js components and language-specific packages directly into their local development environments.