Different models, regions, keys, SDK rules—handled.
You build features. AI Dev Kit calls every provider with one Fluent API.Want AI in your project, or just want to test what the latest AI can possibily do?Doing it yourself is slow: each provider has different models, regions, keys, SDK rules, and rate limits.Even with plugins, you collect many one-provider tools and a lot of repeated code.Use AI Dev Kit.One Fluent API for many providersMinimal code, less setupSchemas/regions/keys/SDK quirks/rate limits — already handledYou focus on shipping features. AI Dev Kit does the calling.It includes everything in Studio and Pro, plus access to:More providers (Microsoft Azure, GroqCloud, Perplexity, xAI…)Enterprise-specific APIs (deployment-aware, region-based, subscription key handling)Early access to experimental featuresBleeding-edge updates on DiscordFor most devs, Pro is enough. You get every feature, including the most recent Agent system and MCP integrations.Research Lab is here for those who need the broadest coverage, the newest providers, and enterprise integration options — as an extended tier.>> Online Documents>> Join Discord Server - get access to pre-release builds & hotfixesWhat's IncludedFluent Runtime API - Write less, do more:Text: text.GENCompletion(), text.GENResponse(), text.GENCode(), text.GENStruct()Image/Video: text.GENImage(), texture2D.GENInpaint(), text.GENVideo()Audio: text.GENSpeech(), audioClip.GENTranscript(), text.GENSoundEffects()// and many others...Optimized for performance, minimal overhead with UniTaskFull provider API coverage (see docs for details)Ollama local server integrationAdvanced Runtime AI Agent (Pro+)Supports all API types:Chat Agent - (ResponsesAPI if supported, ChatCompletionsAPI if not)Assistants Agent - (AssistantsAPI)Voice Agent - (WebSocket-based, RealtimeAPI)Modular Input / Outputs:Input: Text, Image (image understanding), Audio (speech-to-text)Output: Text, Image (image generation), Audio (text-to-speech)Memory:LangChain-like memoryLocal vector storesCapabilities:StreamingModerationFunction CallingWeb SearchCode Interpreter (or Code Execution)File SearchMCPComputer UseLocal Shell CommandsEditor IntegrationsProject-aware AI Chat AssistantVoice supportHighly customizable UIAI Content Generators:Text → PlainText, C#, MonoBehaviour, ScriptableObject, UXMLShader → Surface, Unlit, ImageEffect, Compute, RayTracing, CRTImage → IconArt, Portraits, Backgrounds, Mesh TexturesAudio → Voice Clips, Sound FX, Transcript (Voice Changer coming soon)Mask Painter + Inpainting workflowAudio tools: Waveform viewer, Trimmer, RecorderContext Menu Extenders (right-click > Generate …)[Pro-Only] OpenAI Assistant / Thread Manager[Pro-Only] Uploaded File ManagerModel & Voice ManagementAutomatic AI model/voice updaterAccurate metadata resolverBrowse & compare AI Models / TTS VoicesPrice comparison, voice previewsHistory & Cost TrackingPrompt History ViewerDetailed request logsCost tracking, runtime supportSupported ProvidersOpenAIElevenLabs[Pro-Only] Google Gemini[Pro-Only] Ollama (Local Server)[Pro-Only] OpenRouter[Pro-Only] Anthropic Claude[RL-Only] Microsoft Azure[RL-Only] Groq Cloud[RL-Only] Perplexity[RL-Only] xAI (Grok)Supported PlatformsWindows, macOS, LinuxiOS, AndroidConsolesWebGL (integrated but unstable – testers welcome)This asset uses UniTask under MIT License. See the Third-Party Notices.txt file in the package for license details.
