Integrations
Every provider and runner the family speaks to, what it needs from you, and what it costs.
Providers are infrastructure, not the product. This page is the current list; the principle is on that page.
Motion
| Provider | Where it runs | Cost | Needs |
|---|---|---|---|
| Kimodo (NVIDIA) | Docker on your GPU, another machine, or a rented one | Free locally · per hour rented | Docker, a Hugging Face token, and granted access to a gated Llama 3 model |
| Uthana | Hosted, your account | Metered — per generated or downloaded second | An API key |
Detail: MotionForge providers.
Speech
| Provider | Where it runs | Cost | Needs |
|---|---|---|---|
| ElevenLabs | Hosted, your account | Metered | An API key |
| DeepL (translation) | Hosted, your account | Metered | An API key. Paid plugin |
| Pseudo (translation) | Locally | Free | Nothing — it exists so the pipeline is exercisable with no account |
Detail: SpeechForge providers.
Face
| Provider | Where it runs | Cost | Needs |
|---|---|---|---|
| The engine's own solver | In-process, CPU | Free | Nothing. Models ship with UE 5.8 |
| NVIDIA Audio2Face-3D | A container on your GPU, or a rented one | Free beyond hardware | Docker. The lip-sync models are ungated; only the optional emotion detector is gated |
Detail: FaceForge providers.
Mesh
| Provider | Where it runs | Cost | Needs |
|---|---|---|---|
| TRELLIS.2 (Microsoft) | Docker on your GPU, or a rented one | Free beyond hardware | Docker, and granted access to a gated Meta model |
| Meshy | Hosted, your account | Metered, credits | An API key |
| Tripo | Hosted, your account | Metered, credits | An API key |
Detail: MeshForge providers.
Compute
| What it is | |
|---|---|
| Docker Desktop | How every local runner runs. The hub detects it, and can start it |
| Runpod | Renting a GPU by the hour. Ranked by real per-datacenter stock against a price ceiling; weights persist on a network volume |
| Another machine | Point a project at a runner on a studio workstation. Its token lives in your machine's vault |
| Hugging Face | Where gated model weights come from. One family-wide token |
Engines and frameworks
| Unreal Engine 5.8 | The only supported version today |
| Blender | Optional. The garment solver, the mesh round trip, and a parked motion normalisation pass |
| Narrative Pro | Bridged by separate add-ons — see Narrative Pro add-ons |
| MetaHuman | Supported as a face and body target. No MetaHuman asset is required by the face solver itself |
| Model Context Protocol | Every core plugin ships a toolset |
Two rules about keys
A gated model needs access, not just a token. Two routes here depend on a grant a human at the vendor has to approve, which can take days: the local motion provider's Llama 3, and the local mesh provider's DINOv3.
The motion provider measures whether your token can read its gated model and tells you. The mesh provider does not yet surface its grant on the Keys page — a known gap.
Account-level keys are shared across the family. A Runpod key and a
Hugging Face token belong to you, not to a plugin, so they live at
AutomationForge/Runpod and AutomationForge/HuggingFace and every plugin
reads them. Set once.
See keys.
Adding your own
A provider registers a capability, declares its inputs, says whether it is metered, and reports its readiness. Core plugins never name a vendor, so adding a route is a plugin — not a change to anything above the provider line.
The contract is neutral; the options are the vendor's own, declared by the provider and shown as the vendor names them.