Full Feature List

Everything Onehux AI can do

One platform, one credit balance, unlimited creative and business power.

RAG-Powered Document Chat

Upload any document — PDF, Word, TXT, CSV — and chat with it instantly. Our pgvector-backed retrieval finds the most relevant chunks across your entire knowledge base. Answers include source citations so you always know where information came from. Supports multi-document bases, semantic search, query caching, and conversation history.

Knowledge base Semantic search Source citations Multi-turn memory

RAG Document Chat

Text to Image

Generate photorealistic images, illustrations, and artwork from text prompts in seconds. Choose between FLUX Schnell (40 credits, fast) and FLUX Pro (100 credits, stunning quality). Supports portrait, landscape, and square formats.

FLUX Schnell FLUX Pro v1.1 Up to 1792×1024 Safety filtering

Text to Image

Text to Video & Image to Video

Turn text prompts or still images into high-quality video clips using Kling 1.6. Choose 5-second or 10-second clips. Celery handles background rendering so you can navigate away and come back when it's ready.

Kling 1.6 5s or 10s Text-to-video Image-to-video

Video Generation

Consistent Character Studio

Generate the same person or character across unlimited scenes, outfits, locations, and expressions — preserving facial identity perfectly in every image. Upload one reference photo and iterate forever.

instant-character Scene prompts Identity preservation Negative prompts

Character Studio

Music Generation

Describe any sound — mood, genre, instruments, tempo — and receive an original music clip up to 60 seconds long. Perfect for content creators, podcasters, and game developers. From Afrobeat to classical, ambient to hip-hop.

Stable Audio Up to 60s All genres WAV output

Music Generation

Voice Studio (TTS + Voice Cloning)

Convert any text to lifelike speech using 70+ ElevenLabs voices across 30+ languages including Yoruba, Hausa, and Igbo. Clone any voice from a 1-minute audio sample. Change the voice of an existing recording. Stream audio in real-time for instant playback.

ElevenLabs SDK 70+ voices 30+ languages Voice cloning Speech-to-speech

Voice Studio

Audio Transcription

Upload any audio file (MP3, WAV, M4A) and get an accurate transcript with detected language. Powered by OpenAI Whisper, billed per minute of audio at just 6 credits per minute.

OpenAI Whisper 6 credits/min Language detection MP3 / WAV / M4A

Audio Transcription

Autonomous AI Agents

Deploy AI agents that can use tools, search the web, run multi-step reasoning chains, and complete complex tasks. Configure each agent with custom tools, a system prompt, and a recommended model.

Tool calling Web search Multi-step Custom tools Conversation history

AI Agents

Ready to try all of this?

Start with the free tier — no card needed. Upgrade when you need more.

Get started free