Voice Agent Builder
Talkr's voice agent builder lets you design a conversation as a graph of nodes and pathways. Learn the graph model, the available node types, and where to start.
The Voice Agent Builder is a visual, graph-based editor for designing what your voice agent says and does during a call. Instead of writing one giant prompt, you break the conversation into nodes (stages of the conversation) connected by pathways (the routes the LLM can take between stages, based on how the conversation is going).
Create a new agent from the dashboard — Create Agent → Use Agent Builder generates a starting graph from a description, or Blank Canvas starts from a single pre-filled Start Call node you build up yourself. See Your First Agent in 5 Minutes for a full walkthrough.
The graph model
A workflow is a directed graph:
- Nodes represent a stage of the conversation or an action (e.g. greet the caller, collect an address, transfer the call).
- Pathways (edges) connect nodes and represent the routes the LLM can take depending on what the caller says. The LLM decides at runtime which pathway to follow.
A workflow should have only one Start Call node and typically ends at an End Call node, with Agent nodes and other node types in between. See Editing a Workflow for how nodes, pathways, and node-level toggles fit together.
Node types
| Node | What it does |
|---|---|
| Start Call | Starts the call and configures the agent's greeting. Should have only one per workflow. |
| Agent | Holds the prompt that drives conversation at a given stage; connects to other nodes via pathways. |
| Global | Common instructions (tone, objection handling) prepended to every node with "Add Global Prompt" enabled. |
| QA | Runs automated post-call quality analysis against criteria you define. |
| API Trigger | Exposes an endpoint so external systems (n8n, Zapier, your backend) can start outbound calls. |
| End Call | Configures the agent's final message before the call is terminated. A workflow can have multiple End Call nodes, each with a distinct Prompt. |
| Webhook | Sends call results to an external system (CRM, Zapier, n8n) when a run ends. |
Beyond nodes, you can extend an agent with:
- Tools — let the LLM call external APIs, transfer calls, or invoke MCP servers mid-conversation.
- Knowledge Base — attach documents the agent can reference during a call.
- Pre-Call Data Fetch — enrich context with an HTTP call before the agent starts speaking.
- Pre-recorded Audio — mix in real recordings alongside LLM-generated speech.
- Template Variables — reference
initial_contextandgathered_contextvalues in prompts and payloads.
Where to start
- New to Talkr? Follow Editing a Workflow to learn the fundamentals of nodes and pathways.
- Want to test immediately? Use a Web Call from the agent editor — no telephony setup required.
- Ready to go live? Configure a telephony provider and add an API Trigger or set up inbound routing.
- Need the call to hit your systems? Add a Webhook node to sync results to your CRM or automation tool.
- Want to embed the agent on a website? See Add to Website.