venice-api-kit
由 sabrinaaquino 提供
Coding Agents & IDEs简介
Complete Venice AI API toolkit - image generation, video, audio, embeddings, transcription, characters, models.
描述
该技能的功能
Covers the full Venice AI API through command-line scripts: image generation, editing, upscaling, background removal, video, text-to-speech, transcription, embeddings, and admin functions like billing and key management. All inference runs with zero data retention and no training on your data.
Venice AI retains no request or response data, making it a practical alternative to mainstream inference APIs when privacy matters.
何时使用
- Generating product images from text descriptions
- Removing backgrounds from photos for e-commerce listings
- Converting written content to audio narration with selectable voices
- Transcribing recorded meetings or interviews to text
- Building vector embeddings for a semantic search or RAG pipeline
示例工作流
User asks: Generate a 1536x1024 image of a mountain lake at sunset and save it
- 1
Run image_generate.py with the prompt and --size 1536x1024 flags
- 2
Receive base64 image data from the Venice API
- 3
Decode and write the image to a timestamped PNG file
- 4
Return the output file path
PNG file saved as venice-image-{timestamp}.png in the current directory
前置要求
- Venice.ai account
- VENICE_API_KEY environment variable
安装
clawhub install sabrinaaquino/venice-api-kit运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。