Inworld AI

Documented custom tool support. A Realtime API session registers function definitions in session.tools with a tool_choice setting, and the agent calls them mid conversation to fetch live data or trigger actions the customer's code carries out; tools can change mid session.

SourceInworld, docs.inworld.ai (Using Realtime Models: Function calling)read 2026-09-27

A fixed voice pipeline plus request routing, no workflow model. The Realtime API runs speech to text, the chosen LLM and text to speech as one loop Inworld operates, and the Router picks a model per request by conditional rules, splits and failover. Neither sequences multi step agent work the buyer designs. The graph based Agent Runtime Inworld offered earlier is no longer on its site, and inworld.ai/runtime now redirects to /realtime-api.

SourceInworld, docs.inworld.ai (Realtime Overview, Router Core Concepts)read 2026-09-27

No retrieval over the customer's content. The docs cover TTS, STT, the Realtime API and the Router; the Router's web search grounds answers in the public web, which is not the customer's corpus, and context otherwise arrives in the prompt or through the customer's function calls. No knowledge base, index or ingestion is documented.

SourceInworld, docs.inworld.ai (llms.txt, Router Web search)read 2026-09-27

Guardrail building blocks the customer places, no approval step. Router moderation endpoints classify standalone text or whole conversations against OpenAI compatible and AILuminate safety categories, so the customer can screen user input before the LLM and filter output before users see it, and tool_choice limits which tools a session may call. No mechanism holds an agent action for a person; the constraints are ones the customer sets.

SourceInworld, docs.inworld.ai (Moderations, Using Realtime Models)read 2026-09-27

Access runs through team accounts with organization roles managed by Owners and Admins, SAML 2.0 SSO through the customer's identity provider on verified domains with a require SSO option, and SCIM 2.0 provisioning of members and roles on Enterprise. The inworld.ai/security page states that Inworld is SOC 2 Type II certified and HIPAA and GDPR compliant, and the regions page says SOC 2 Type II applies across deployments; zero data retention is configurable per organization or workspace.

SourceInworld, docs.inworld.ai (SAML Single Sign-On, Team Management, Regions) and inworld.ai/securityread 2026-09-27

Usage and routing metrics, no per session trace. The Portal's Usage page breaks spend down by model across TTS, STT and LLMs, and Router data integrations export routing exposure to BigQuery or Mixpanel. No view of a session's turns, tool calls and outputs is documented, so the reporting stays at the aggregate level.

SourceInworld, docs.inworld.ai (Usage, Router Data Integrations)read 2026-09-27

Session memory with a stated lifetime; the long term store is the customer's. With providerData.memory on, the server extracts durable facts and a running summary during a session and holds them for the life of the WebSocket plus a 15 minute idle TTL. Inworld's guide says server side memory is then gone, and long term memory means the customer saves the facts in its own database keyed by user and seeds the next session. What Inworld itself keeps is conversation state inside a session.

SourceInworld, docs.inworld.ai (Long-term Memory)read 2026-09-27

Named regions offered as an option. Beside the US deployment, Inworld runs fully isolated EU and India regions, each a complete stack with inference, APIs, Portal, databases and storage in region, provisioned per organization on Enterprise; inworld.ai/llms.txt also lists VPC deployment on Enterprise.

SourceInworld, docs.inworld.ai (Regions) and inworld.ai/llms.txtread 2026-09-27

No packaged agents. The current docs offer voices (a shared Voice Library, voice cloning and design) and quickstarts, not agents a buyer adopts. The templates that came with the earlier Agent Runtime are no longer on Inworld's site.

SourceInworld, docs.inworld.ai (llms.txt, Voice Sharing, Realtime Quickstart)read 2026-09-27

People reach the agent over voice and the web. Realtime sessions open over WebSocket or browser WebRTC, and phone calls reach the agent through Twilio Media Streams or ConversationRelay. Every session starts when a user connects or calls or the customer's application opens it. No schedule, event or webhook that starts an agent is documented.

SourceInworld, docs.inworld.ai (Twilio Integration, WebRTC Connection)read 2026-09-27

The customer chooses and routes models. The Router exposes 220+ LLMs from OpenAI, Anthropic, Google, Meta, Mistral and others plus Inworld hosted open models behind one OpenAI compatible endpoint, with per request model choice, conditional routing on request metadata, traffic splitting and provider failover the customer configures. A Realtime session sets its LLM by modelId and can switch mid session.

SourceInworld, docs.inworld.ai (Router Introduction, Traffic Splitting, Using Realtime Models)read 2026-09-27

A documented API and SDKs for Inworld's own platform. REST and WebSocket APIs for TTS, STT and the Realtime API (WebSocket and WebRTC), an OpenAI and Anthropic compatible Router with a router management API (create, list, update, delete routers), Python and Node.js SDKs, and an Inworld CLI with a built in MCP server exposing its operations as tools.

SourceInworld, docs.inworld.ai (llms.txt, API reference, Inworld CLI)read 2026-09-27

An optimization loop on the deployed agent. Router traffic splitting sends weighted shares of live traffic to model variants for A/B tests, and custom metrics built from the customer's imported product events (BigQuery, Mixpanel) are attached to routers to measure each variant's impact. The variable under test is the agent's model, and the outcome measured after deployment is the customer's own KPI.

SourceInworld, docs.inworld.ai (Traffic Splitting, Custom Metrics)read 2026-09-27

No browser, desktop or computer control; the browser appears only as a WebRTC client for voice sessions.

SourceInworld, docs.inworld.ai (llms.txt, WebRTC Connection)read 2026-09-27