32 Services from api.venice.ai

Transcribes an uploaded audio file into text using AI speech-to-text models, optionally returning timestamps and duration.

Run multimodal text inference (chat completions) against a specified model, supporting text, images, audio, video, and file inputs with optional web search and streaming.

Searches the web using Brave or Google and returns structured results with titles, URLs, content snippets, and dates — with privacy-preserving query handling.

Extracts text content and token count from uploaded document files (PDF, DOCX, PPTX, XLSX, plain text) with zero data retention

Removes the background from an image using AI, returning a PNG with a transparent background

Upscales an image by a configurable scale factor (1–4x) and optionally enhances it with AI-driven style and detail improvements.

Queues a new AI video generation request, returning a queue ID for tracking the async result.

Converts text (up to 4096 characters) into audio using a choice of TTS models and voices, returning binary audio in the requested format.

Scrapes a public web page and returns its full content converted to Markdown format

Queues an asynchronous audio generation request (music, speech, or narration) using a specified model and prompt, returning a queue ID for polling.

Tops up a Venice AI credit balance using an x402 micropayment (USDC on Base or Solana), returning the credited amount and new balance.

Edit or modify an existing image based on a text prompt, returning the modified image as binary output.

Converts text or token arrays into vector embeddings using a choice of embedding models, OpenAI-compatible API.

Generates one or more images from a text prompt using configurable AI models, returning base64-encoded image data

Clone a voice from an audio sample to produce a reusable voice handle for speech synthesis on Venice AI's TTS models.

Generates images from a text prompt using Venice's AI models via an OpenAI-compatible endpoint, returning base64 or data URL images.

Returns a paginated, filterable list of AI characters available on the Venice platform, with support for search, tags, categories, model, and sort options.

Creates a structured model response using the OpenAI-compatible Responses API format, returning typed output blocks including reasoning, messages, function calls, and web search results.

Returns current API key rate limits, tier information, balances, and access permissions for the authenticated Venice AI user.

Retrieves paginated billing usage records for the authenticated Venice AI user, with filtering by date range and currency.

Returns aggregated API usage analytics for the authenticated user, broken down by date, model, and API key, with daily trend data.

Polls for the status or retrieves the completed result of a previously queued video generation request on Venice AI.

Transcribes the audio from a YouTube video URL into text, returning the transcript and detected language.

Edit or modify an image using up to three layered inputs (base image plus masks/overlays) with a text prompt.

Polls the status or retrieves the result of a queued audio generation request by model and queue ID

Returns the authenticated user's current DIEM and USD billing balances, consumption currency, and total DIEM epoch allocation for the Venice AI platform.

Returns the last 50 rate limit violation events for the authenticated account, including which API key, model, tier, and limit type was exceeded.

Marks a video generation request as complete and deletes it from storage after successful download.

Marks an audio generation request as complete and deletes the generated media from storage after successful download.

Executes JSON-RPC calls against a specified blockchain network via Venice AI's private API gateway

Permanently deletes a specific API key from a Venice AI account by its ID.

Returns the list of available AI models accessible through the Venice.ai x402-enabled gateway.