Voice synthesis, LLM inference, vision analysis, and web search. A unified API for your AI-powered applications.
// Generate speech from text
POST /v1/tts
{
"text": "Hello, I'm Marcus from DragonFire AI.",
"voice_id": "george"
}
// Returns: audio/mpegEverything you need to build intelligent applications
18 natural voices. Text-to-speech with emotion and clarity.
POST /v1/audio/speechLLM inference with multiple models. From fast small models to deep-thinking larger ones. Standard chat completions shape.
POST /v1/chat/completionsImage understanding and analysis. Describe, extract text, answer questions about images.
POST /v1/chat/completionsPrivacy-focused web search. Get real-time results without tracking your users.
POST /v1/web/searchSpeech-to-text transcription. Convert audio to text with high accuracy.
POST /v1/audio/transcriptionsAI image generation. Create images from text prompts.
POST /v1/images/generationsAI video generation from text or image seeds.
POST /v1/video/generationsContent plus JSON Schema, out comes structured JSON. Turn unstructured pages into data.
POST /v1/extractLow latency inference via Unix Domain Sockets for local services
RESTful API with the standard request shapes your existing tooling already speaks
API key authentication with per-user rate limiting
Built for distributed inference across the DragonCloud mesh
Self-serve signups aren't open yet — we're finalising sovereign account primitives (mnemonic + wallet) first. Join the Signal group to request a test key and get pinged when the front door opens.
Join the Signal Group