Skip to main content

api.voxvey.com

Voxvey API

Get building fast using Voxvey's APIs

Start integratingView endpointsOpenAPI JSON

API Surfaces

Start with the exact endpoint you need.

Chat Completions

Message-based model calls with OpenAI-compatible request and response shapes.

POST /v1/chat/completionsResponses

Response-style model calls for richer input, tools, and provider-specific response fields.

POST /v1/responsesMessages

Messages API calls for clients and gateways that expect /v1/messages.

POST /v1/messagesEmbeddings

Text vectorization for search, clustering, and retrieval workflows.

POST /v1/embeddingsImages

Generate and edit images with provider-prefixed image models.

POST /v1/images/generationsVideos

Create, poll, edit, extend, and download async video jobs.

POST /v1/videosRealtime Calling

Create low-latency sessions for interactive text and audio applications.

POST /v1/realtime/client_secretsText-to-Speech

Generate speech audio from text using supported provider-prefixed models.

POST /v1/audio/speechTranscriptions

Upload audio with multipart form data and receive transcription text.

POST /v1/audio/transcriptions

Request Basics

The shared model routes use provider-prefixed model IDs and familiar endpoint payloads.

  1. Send a Voxvey bearer token with the request.
  2. Choose a provider-prefixed model ID such as openai/gpt-4o-mini.
  3. Use the request body shape that matches the endpoint.
  4. Inspect response usage to understand settled credit consumption.

Reference

Use the endpoint pages for examples, or inspect the published OpenAPI document for complete schemas and response shapes.

Browse endpoint reference