# Ino AI Platform API

> What the API does — speech, transcription, voices, images, video, skyboxes, templates and agents — and where to start.

Every page below is Markdown, written for people and agents alike. https://docs.lumavox.ai/llms-full.txt is every guide in one file; the API reference's sections are linked one by one. The API is at https://api.lumavox.ai; its OpenAPI document is https://api.lumavox.ai/openapi.json. Every request but `GET /health` needs `Authorization: Bearer <API key>`, except an agent's conversations, which take an end user's ephemeral token.

## Get started

- [Overview](https://docs.lumavox.ai/index.md): What the API does — speech, transcription, voices, images, video, skyboxes, templates and agents — and where to start.
- [Quickstart](https://docs.lumavox.ai/quickstart.md): Create an API key, turn text into speech, then queue an image and poll it until it is ready.
- [Authentication](https://docs.lumavox.ai/authentication.md): How to send an API key, which scopes a key needs, the master key, ephemeral keys for end users, and 401 versus 403.
- [Conventions](https://docs.lumavox.ai/conventions.md): How every endpoint writes times, credits, durations, ids and lists, how it pages, and what null and an absent field mean.
- [Errors and limits](https://docs.lumavox.ai/errors.md): The error envelope, every error code and what to do about it, request ids, rate limits, and retrying safely.
- [Queued jobs](https://docs.lumavox.ai/jobs.md): Which endpoints answer 202 with a gen_… id, how to poll them, what each status means, and when a job is charged or refunded.
- [Credits and usage](https://docs.lumavox.ai/usage.md): How credit works, how to read your balance and usage from the API, what a 402 means, and which plan limits you can run into.
- [Limits](https://docs.lumavox.ai/limits.md): Every limit the platform holds an organisation to besides its plan's, as its staff set it, and how to read them from code.

## Speech

- [Text to speech](https://docs.lumavox.ai/speech/text-to-speech.md): Turn text into speech in one request with POST /v1/tts — voices, models, WAV or raw PCM, sample rates and streaming.
- [Stored audio](https://docs.lumavox.ai/speech/stored-audio.md): Queue speech with POST /v1/audio for mp3, Opus or WAV files up to 5,000 characters, kept in your asset library.
- [Transcription](https://docs.lumavox.ai/speech/transcription.md): Turn speech into text — POST /v1/stt for short audio, streamed segments for long recordings, POST /v1/transcriptions for large files.
- [Voices](https://docs.lumavox.ai/speech/voices.md): List the voices you can speak with, clone one from a recording, design one from a description, and edit or delete your own.

## Images and video

- [Images](https://docs.lumavox.ai/media/images.md): Generate an image from a prompt and up to eight reference pictures, then poll until it is ready and fetch it from your library.
- [Video](https://docs.lumavox.ai/media/videos.md): Generate a 5–20 second clip from a prompt, optionally opening and closing on images from your library, and poll until it is ready.
- [Skyboxes](https://docs.lumavox.ai/media/skyboxes.md): Generate a 360° environment — an 8K HDRI to light a 3D scene, an equirectangular PNG, a depth map and a web preview — for one flat price.
- [Templates](https://docs.lumavox.ai/media/templates.md): Run a generation someone has already designed — fill in a picture or a prompt, pay the price quoted up front, and poll the result like any other.

## Agents

- [Agents](https://docs.lumavox.ai/agents.md): What an agent is, how to author and configure one, and how a conversation with it fits together from your server to your user's device.
- [End users and their keys](https://docs.lumavox.ai/agents/end-users.md): Register the people your agents talk to, and mint each one a short-lived, prepaid ephemeral key that their device uses to hold a conversation.
- [Conversations and memory](https://docs.lumavox.ai/agents/conversations.md): Open, continue, read and delete conversations with an agent, what each turn costs, and how facts and relationships carry from one conversation to the next.
- [The WebSocket](https://docs.lumavox.ai/agents/websocket.md): The agent's socket protocol in full — connecting, every frame you send and receive, audio in and out, interruptions, limits and close codes.
- [Knowledge](https://docs.lumavox.ai/agents/knowledge.md): Give your agents reference material, written, from a web page or from a file, that they look up by meaning, and choose which agent reads which entry.
- [Tools](https://docs.lumavox.ai/agents/tools.md): Give your agents tools to call while they reply — your server, your app, and two of Gemini's own — turned on per agent.

## Library

- [Assets](https://docs.lumavox.ai/library/assets.md): The library of everything your organisation has generated or uploaded — list and search it, upload files, organise them into folders, delete them.
- [Generations](https://docs.lumavox.ai/library/generations.md): List every queued generation your organisation has made, across all capabilities, and find one again by id — the way back to a lost id and to reconcile.

## SDKs

- [Server SDK](https://docs.lumavox.ai/sdks/server.md): The TypeScript client for your backend — install, errors, paging, waiting on jobs, uploads and streams, with your organisation's API key.
- [Client SDK](https://docs.lumavox.ai/sdks/client.md): Talk to agents from a browser, a React Native app or Node with an end user's key — a conversation that keeps itself connected, and their memory.
- [React](https://docs.lumavox.ai/sdks/react.md): Hooks for React and React Native over the client SDK — a conversation in a component, and the person's sessions, facts and relationships.
- [React Native](https://docs.lumavox.ai/sdks/react-native.md): Voice conversations with agents in a React Native app on iOS, Android and the web — the client, the hooks, and push-to-talk, half-duplex and hands-free audio.

## API reference

- [API reference](https://docs.lumavox.ai/reference.md): Every operation the API publishes, generated from its OpenAPI document.
- [Text to speech](https://docs.lumavox.ai/reference/tts.md): Speech generation.
- [Images](https://docs.lumavox.ai/reference/images.md): Image generation.
- [Video](https://docs.lumavox.ai/reference/videos.md): Video generation.
- [Skyboxes](https://docs.lumavox.ai/reference/skybox.md): 360° environments — an 8K HDRI for lighting a 3D scene, an equirectangular PNG and a depth map.
- [Templates](https://docs.lumavox.ai/reference/templates.md): Generations somebody has already designed — the prompt, the size, every parameter — leaving only the media inputs for you to fill.
- [Stored audio](https://docs.lumavox.ai/reference/audio.md): Speech as a queued generation — stored, and the only door that encodes mp3 or opus.
- [Transcription](https://docs.lumavox.ai/reference/transcription.md): Speech to text — inline for short audio, `stream=true` for newline-delimited segments, queued for long.
- [Voices](https://docs.lumavox.ai/reference/voices.md): The voices a key may speak with, and — on `voices:write` — adding, designing, editing and deleting your own.
- [Agents](https://docs.lumavox.ai/reference/agents.md): Authoring agents: the characters `/v1/agent/*` talks to, their organisation-wide defaults, and what each may look up.
- [Knowledge](https://docs.lumavox.ai/reference/knowledge.md): What you tell your agents — entries an agent can look up by meaning, written and assigned from your own systems.
- [Tools](https://docs.lumavox.ai/reference/tools.md): What your agents can call while they reply — your server, signed, or the person's app over the WebSocket — each turned on per agent.
- [Conversations](https://docs.lumavox.ai/reference/agent.md): Conversations with an agent.
- [Assets](https://docs.lumavox.ai/reference/assets.md): The library — everything your services have produced and you have uploaded.
- [Generations](https://docs.lumavox.ai/reference/generations.md): Every generation across every capability, in one list — the way back to an id you lost, and the reconciliation loop.
- [Usage](https://docs.lumavox.ai/reference/usage.md): What your organisation has spent, and what it has left.
- [End users](https://docs.lumavox.ai/reference/end-users.md): The people your agents talk to and you generate on behalf of.
- [Ephemeral keys](https://docs.lumavox.ai/reference/ephemeral-keys.md): Short-lived tokens for one end user's device, with their own credit ceiling.
- [System](https://docs.lumavox.ai/reference/system.md): Health and metadata.

## For AI agents

- [For AI agents](https://docs.lumavox.ai/ai.md): How an AI agent or coding assistant reads these docs — llms.txt, a Markdown copy of every page, and the OpenAPI document.

## Optional

- [Every guide in one file](https://docs.lumavox.ai/llms-full.txt): every page above but the reference's sections, in order
- [OpenAPI document](https://api.lumavox.ai/openapi.json): the contract, as the API serves it