# Assemblix

> Visual builder for conversational AI agents. Design the whole dialogue as a graph — branching logic, any LLM, your own docs — then ship it as text, real-time voice, or a lip-synced AI avatar. Every agent is also a typed HTTP endpoint.

## What it is

Assemblix is a visual builder for conversational AI agents. Instead of writing one long prompt, you design the whole conversation as a graph: agent nodes, condition nodes that branch on intent or typed state, knowledge bases, and tool calls. Any agent in that graph can answer as plain text, as real-time streamed voice, or as a live lip-synced AI avatar — the output modality is a single field on the agent, so adding voice never means rebuilding the flow. Every published agent is also an authenticated HTTP endpoint your own product can call. It is an alternative to Voiceflow, ElevenLabs Agents, Flowise and n8n for teams that want explicit control over the dialogue, typed state that survives restarts, step-by-step execution replay, and the option to self-host the whole stack.

## Key capabilities

- **Branch on anything** — Condition nodes route the conversation on intent, on state, on a tool's answer. Every path is visible, so nothing hides inside a prompt.
- **A model per node** — Classify on a cheap fast model, reason on a strong one. The provider is a property of the node, not of the project.
- **Real nodes, not blocks** — Agent, Condition, Delay, Set Variable, Transcribe, HTTP Request. Reach anything over HTTP, then keep going in the graph.
- **Output: Text** — Plain chat replies.
- **Output: Voice** — Speaks out loud, streamed live as it thinks.
- **Output: AI avatar** — A talking face on screen.
- **Agents that remember** — Typed workflow and agent state carries context across every turn — set it, branch on it, watch it update. The values live in Postgres, so a conversation survives restarts, deploys, and weeks of silence.
- **Answer from your own docs** — Upload PDFs, paste text, attach the knowledge base to any agent. It retrieves over your material and answers with citations — no fine-tuning, no separate vector database to run.
- **Every agent is also a typed endpoint.** — Hit publish and you get POST /api/workflows/wf_… with bearer auth and a stable contract. Put it behind your own product, your own UI, your own funnel — no separate deploy, no infrastructure code.

## Supported providers

- OpenAI (LLM)
- Gemini (LLM)
- DeepSeek (LLM)
- ElevenLabs (Voice)
- Anam (Avatar)
- Yandex SpeechKit (Voice · STT)

On the free tier you can run on our keys to get started. After that the cost of a call is between you and the provider.

## API example

```bash
curl -X POST https://app.assmblx.com/api/workflows/wf_a3f2 \
  -H "Authorization: Bearer $ASSEMBLIX_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": { "message": "I want a refund" },
    "state": { "user_id": "u_42" }
  }'
```

Response:

```json
{
  "executionId": "exec_d7c9b585",
  "status": "completed",
  "output": {
    "parsed_message": {
      "intent": "refund",
      "confidence": 0.94,
      "next_action": "check_policy"
    },
    "tool_executions": []
  },
  "state": { "user_id": "u_42", "turn": 3 },
  "metadata": { "durationMs": 850, "totalSteps": 3 }
}
```

## Pricing

- **Free** — $0 forever. For prototyping and weekend hacks.
  - 3 workflows · 3 endpoints
  - 1,000 API calls / month
  - 1 provider
  - Community support
- **Pro** — $29 /mo. For production solo and small teams.
  - Unlimited workflows & endpoints
  - 50,000 API calls / month
  - All providers + fallback chain
  - Durable runs up to 30 days
  - Priority support
- **Team** — $99 /seat/mo. For scale and collaboration.
  - Everything in Pro
  - 250,000 API calls / month
  - RBAC + SSO
  - Audit log
  - SLA

Need enterprise / SLA? Talk to us →

## Secondary pages

- [Privacy](https://assmblx.com/privacy)
- [Terms](https://assmblx.com/terms)
- [Contact](https://assmblx.com/contact)
- [Docs](https://assmblx.com/docs)