Covers two ways to authenticate with the Venice API: Bearer API keys for account-based access, and x402/SIWE wallet signing for pay-per-request usage without an account.
Maps the full Venice.
Generates music, jingles, and long-form audio through Venice AI's async API.
Lets you browse, search, and filter Venice AI's public character catalog.
Converts text to speech through Venice AI's API with nine TTS model families, each with its own voice set.
Transcribes audio files to text through Venice AI's speech-to-text API.
Covers Venice AI's three billing API endpoints: checking account balance, pulling per-request usage ledgers in JSON or CSV, and querying aggregated usage analytics by date, model, or API key.
Manages Venice AI API keys through REST endpoints: create, list, update, and revoke both INFERENCE and ADMIN keys.
Generates images from text prompts using Venice AI's API.
Generates videos from text, images, or existing video through Venice's async API.
Calls Venice's OpenAI-compatible chat completions endpoint with support for web search, end-to-end encryption, multimodal inputs, tool calling, structured output, and prompt caching.
Edits existing images through Venice's API.
Queries Venice AI's model catalog to get capabilities, constraints, and pricing for text, image, video, music, and other model types.
Generates vector embeddings through Venice's API using an OpenAI-compatible endpoint.
Calls Venice's /responses endpoint, which returns a typed output array with separate blocks for reasoning, messages, function calls, and web search events.