Every video is a pipeline.
A real node graph with a growing library of tools: generation, audio, captions, compositing, publishing. Wire them into pipelines that branch, fan out, and drop into code.
The node editor for
generative media.
Build AI video, image, and audio workflows with models, tools, data, and security built in.
Generate, edit, and publish in one place
Describe the video, tweak the cut, and let it publish itself.
Ask for it in plain language.
Brief it like a production team. Ask for captions burned in or a score underneath and it does that too, and anything you want repeated becomes a pipeline you can open and put on a schedule.
Edit in the built-in timeline.
Ask the AI assistant for the cut in plain language and it edits the timeline for you. Nudge it by hand, then export in the ratio you actually publish.
Powered by the best generative models
Pick a model for every step, swap it anytime, no lock-in. New models drop in the day they’re released.
Video
Cinematic clips from a prompt, duration, aspect ratio, and audio per model.
- Veo 3.1
- Veo 3.1 Fast
- Kling 3.0 Pro
- Seedance 2.5
- +8 more
Image
Product shots, illustrations, and campaign art, resolution and aspect per model.
- Gemini 2.5 Flash Image
- Gemini 3.1 Flash Image
- FLUX.2 Pro
- Seedream 4.5
- +5 more
Language
Drafting, rewriting, classification, and reasoning, from frontier models to open weights.
- Claude Sonnet 5
- GPT-5
- Gemini 3.1 Pro
- Llama 3.3 70B
- +3 more
Speech & audio
Voiceovers, narration, music, sound effects, and transcription.
- ElevenLabs v3
- ElevenLabs Multilingual v2
- Lyria 3 Pro
- Whisper Large v3
- +4 more
Veo 3.1
Video
Veo 3.1 Fast
Video
Kling 3.0 Pro
Video
Seedance 2.5
Video
Seedance 2.0
Video
Grok Imagine
Video
Grok Imagine 1.5
Video
Wan 3.0
Video
Wan 2.7
Video
Veo 3.1 Lite
Video
HappyHorse 1.1
Video
Seedance 1.5 Pro
Video
Gemini 2.5 Flash Image
Image
Gemini 3.1 Flash Image
Image
FLUX.2 Pro
Image
Seedream 4.5
Image
Seedream 5.0
Image
Nano Banana Pro
Image
RE
Recraft V4.1
Image
GPT Image 2
Image
Qwen Image 3
Image
Claude Sonnet 5
Language
GPT-5
Language
Gemini 3.1 Pro
Language
Llama 3.3 70B
Language
DeepSeek R1
Language
Qwen2.5 72B
Language
Mixtral 8x22B
Language
ElevenLabs v3
Speech & audio
ElevenLabs Multilingual v2
Speech & audio
Lyria 3 Pro
Speech & audio
Whisper Large v3
Speech & audio
HE
Kokoro 82M
Speech & audio
Voxtral Mini TTS
Speech & audio
Gemini Flash TTS
Speech & audio
ElevenLabs SFX
Speech & audio
- $5
- to start, prepaid credits, no subscription
- $1.06
- typical cost of one AI video generation
- 82
- narration voices across four speech models
- 24/7
- pipelines publish while you're away
The platform behind the pipeline
Models, pipelines, and APIs, built to ship, not just to demo.
Visual pipeline builder
Wire models, guardrails, and integrations together on a drag-and-drop canvas. No glue code.
Learn moreOne API, two ways to call it
Every pipeline gets a versioned endpoint: typed /invoke or OpenAI-compatible /chat/completions. Point any OpenAI SDK at it, streaming included.
Learn moreBring any model
Pick a model per node: Veo, Seedance, Gemini, or any open model. Swap anytime, never locked to one provider.
Learn moreVision QC on every render
A vision model samples frames and checks the output really shows what you asked for. A wrong subject fails the run before it can publish.
Learn moreFootage in, clips out
Pull video from any URL, transcribe it with word-level timings, cut the highlight, reframe to vertical, and burn captions. A two-hour episode becomes a week of Shorts.
Learn moreProduction-ready
Automatic retries and fallback models, KMS-encrypted secrets, and your choice of runtime on Enterprise: bring your own cloud, or hardware-attested Treza Enclaves.
Learn moreBuilt by people from
We've built pipelines, infrastructure, and platforms at global scale.
Common questions
What people ask before their first generation.
What can I generate with Treza?
Video with Veo 3.1 and Seedance 2.5, images with Gemini image models, and text with open models like Llama, DeepSeek, and Qwen, plus transcription and embeddings. Each generator is a node on a canvas, so one prompt can drive several modalities in a single pipeline.
Do I have to build the pipeline myself?
No. Describe what you want published in the Treza chat, or connect Claude over MCP and ask from there. Treza drafts the pipeline for you: models picked, nodes wired, schedule set. Run it as is, or open the canvas and tweak any node.
How is this different from a single AI generator?
A one-shot generator gives you one output from one model. Treza runs the whole workflow: one node can refine your brief into a proper shot prompt, the next renders the video, another drafts the caption. Then the entire pipeline publishes as an API you can call from your product.
Which models can I use?
The catalog covers the major open families (Llama, Mistral, Qwen, DeepSeek, Gemma, Phi) alongside Veo, Seedance, and Gemini image models for media. Not listed? Type any Hugging Face or OpenRouter model id straight into the node. Swap models per node, never locked to one provider.
Do I have to rewrite my code?
No. Every pipeline exposes an OpenAI-compatible /chat/completions endpoint, streaming included. Point any OpenAI SDK at it: change the base URL and API key and you’re done. Prefer a native integration? Call the typed /invoke endpoint, with JSON inputs and outputs derived from the graph.
Can I see what each generation did?
Yes. Every run is logged with per-node timing, tokens, and success rate, so you can see exactly how a prompt became an output. Version and roll back any pipeline, and export run history any time.
How much does it cost?
There's no subscription. You buy prepaid credits (starting at $5) and spend them as you run models, with only successful runs charged. Credits never expire. Enterprise adds a private deployment, SSO, postpaid invoicing, and custom contracts.
Is there an enterprise plan?
Yes. Enterprise covers what a studio, agency, or brand needs before it can put Treza into production: custom nodes and workflows built for your pipeline, a deployment in your own cloud or on-prem, C2PA content credentials, SSO, a forward deployed engineer, and volume pricing with postpaid invoicing. Tell us what you produce and we'll scope it with you. See Treza for Enterprise
Video · Image · Audio
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.