API reference · v1

API Reference

One REST API for uncensored image, video, voice and chat generation. Every endpoint takes JSON (or a file upload), returns JSON or audio, and bills per generation from your balance.

Building with an AI assistant? Point it at /llms.txt or append .md to any reference page.

Core

GET/v1/modelsList every model available to your account.GET/v1/accountRead your balance and account status.DELETE/v1/end-users/{user}Erase what was generated for one of your users, for their privacy requests.

Images

POST/v1/images/generationsGenerate images from a text prompt.POST/v1/images/editsEdit an image you generated earlier, guided by a prompt. One to six outputs per call.GET/v1/imagesList the images your account has generated.GET/v1/stylesThe art styles for `style` on image and video generation. No key needed.GET/v1/images/actionsThe ready-made explicit stills for `action` on `spicy-image-action-1`. No key needed.

Moderation

POST/v1/moderationsRun a prompt or conversation through the same screen the generation endpoints use, without generating.POST/v1/moderations/appealsTell us a declined request should have been allowed.

Characters

POST/v1/charactersSave a reusable identity from your own generated images, to get the same person again across images, edits and video.POST/v1/characters/importBring an existing AI-generated character over from your own platform. Only for verified businesses with an open import window.GET/v1/charactersYour saved characters, newest first.DELETE/v1/characters/{id}Remove a saved character. Its reference sheet stays in your image library.

Audio

POST/v1/audio/speechTurn text into speech. Returns a durable audio URL you can pass straight to video generation as `audio_url`, or streams the audio as it is synthesized.POST/v1/audio/transcriptionsTurn speech into text: voice notes, clips and call recordings.POST/v1/voicesClone a voice from one of your clips with the speaker's consent (voice design is paused). Custom voices are spoken by `spicy-voice-1-custom`.GET/v1/voicesEvery preset voice with the models that speak it, then your designed and cloned voices, newest first.DELETE/v1/voices/{id}Delete one of your designed or cloned voices.POST/v1/audioUpload a short audio clip for lip-sync and audio-guided video. The clip is transcribed and screened before it can be used.GET/v1/audioYour audio clips, uploaded and generated, newest first.DELETE/v1/audio/{id}Forget a clip so it can no longer be used as a video input.

Video

POST/v1/videos/generationsStart a video generation. Returns a task to poll.GET/v1/videos/tasks/{id}Check a video task and collect the finished clip.POST/v1/videos/editsEdit a clip you generated from a prompt (outfit, style, lighting, props), or transfer a clip's motion onto the person in one of your images. Returns a task to poll.GET/v1/videos/motionsThe curated motion clips for motion transfer on `spicy-animate-1`. No key needed.GET/v1/videos/actionsThe ready-made sex acts for `action` on `spicy-motion-3` and `spicy-motion-3-fast`. No key needed.

Chat

POST/v1/chat/completionsOpenAI-compatible uncensored chat and role-play, with streaming.

Embeddings

POST/v1/embeddingsTurn text, or images from your own library, into vectors for memory, search, recommendations and near-duplicate detection. OpenAI-compatible.

Live calls

POST/v1/realtime/sessionsStart a live voice call with a companion: returns a one-time WebSocket URL your client (a browser too) connects to, without ever seeing your API key.GET/v1/realtimeThe call itself: a WebSocket (wss://) opened with the session ticket. Send microphone audio, receive the persona's voice and transcripts as JSON events.

Base URL

https://api.spicyapi.com/v1

For assistants

/llms.txt /llms-full.txt