venice-models
by sabrinaaquino
Coding Agents & IDEsBrief
Explore Venice AI's available models - LLMs, image generators, video, TTS, ASR, and embeddings.
Description
What This Skill Does
Toolkit for the Venice AI API covering image generation, video, audio, embeddings, transcription, characters, and admin functions. All inference runs with no data logging or retention. Scripts are invoked from the command line using uv and Python.
Venice AI retains no request or response data, making it suitable for inference tasks involving sensitive or proprietary content where standard cloud AI providers are not an option.
When to Use It
- Generate images from text prompts without data retention
- Remove backgrounds from product or portrait photos
- Transcribe recorded meetings or interviews to text
- Convert written content to spoken audio with custom voices
- Build semantic search pipelines using vector embeddings
Example Workflow
User asks: generate an image of a mountain at sunset, then upscale it 2x with cinematic enhancement
- 1
Run image_generate.py with the prompt to produce a PNG saved with a timestamp filename
- 2
Pass the output file to image_upscale.py with --scale 2 --enhance --enhance-prompt "cinematic lighting"
- 3
Return the upscaled PNG path to the user
Upscaled PNG saved locally as upscaled-{timestamp}.png
Requirements
- VENICE_API_KEY environment variable (obtain from venice.ai Settings > API Keys)
- Venice AI account
Installation
clawhub install sabrinaaquino/venice-modelsRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.