Strongly Certified · Multi-Agent Voice

Multi-Agent Dispatch

Two specialist voice agents. One continuous call.

A working blueprint for the agent hand-off pattern. Aria takes the inbound dispatch call. Shipment status, carrier dialling, multilingual replies. The moment the caller asks about pricing, Aria hands the live audio to Theo, the rate negotiator, with the full conversation already loaded. The caller hears one voice change, never a hold-and-transfer. Two personas, one WebSocket, zero lost context.

Talk to an Engineer See What It Does Why You Need Hand-off

2 agents

One continuous call

Mid-call

Specialist hand-off

Full

Context carryover

What it does

The voice loop, end-to-end.

No black box. Each step is a typed-frame node you can edit, monitor, and replace.

Aria takes the call. Inbound dispatcher conversation: shipment status, customer profile lookups, outbound calls to drivers. Multilingual, warm, brisk. Switches language automatically when the caller does.

Caller asks about rates. Aria recognises the topic, summarises what she's captured so far, and calls a single hand-off tool. The streaming runtime opens Theo's vendor session in parallel. Caller never hears hold music.

Theo activates with full context. Aria's conversation history flows into Theo's session prompt. No re-asking "what was your name again?". The verified caller, the shipment, the lane, the asked-for rate are all already loaded.

Theo negotiates, stays in lane. Rate discussion only. Anything outside pricing (billing, new shipments, account changes) gets persona-redirected back to dispatch. Same call, specialist voice, no scope creep.

Capabilities

Built for production. Day Two-ready.

Streaming graph contract, observability, and cost discipline come standard. The agent ships with a full test suite that runs in CI on every node version bump.

Single-node voice loop

Replaces VAD + STT + LLM + TTS with one realtime model. Lower latency, fewer billing lines, fewer integration points. The standard chain stays available for mix-and-match deployments.

aiortc-freeServer VADOne billing line

Steerable mid-session

SteerFrame on steer_in mutates the live session via session.update. Voice + instructions swaps defer until response.done so providers don't reject mid-response changes; temperature + turn-detection swaps apply immediately.

SteerFrameLive mutationNo session restart

Audio-only or audio+text

modalities config swaps between audio (no transcript-delta emission) and audio_text (transcript on text_out). Saves provider tokens when no downstream node consumes the transcript.

modalities configOptional transcriptToken-conscious

Provider-agnostic config

OpenAI Realtime + Gemini Live both supported through the same node via STRONGLY_SERVICES routing. Provider_param_overrides escape-hatch for new provider knobs without forking the node.

AI Gateway routingPer-provider tuningForward-compat

Same span path as batch

Per-frame spans land in workflow_spans (Mongo), same path the batch runtime uses, same canvas viewer. No Prometheus, no Grafana, no external tracing.

ADR-S14Strongly tracingCanvas-first

Typed bridge failures

RealtimeAuthError, RealtimeProtocolError, RealtimeAudioFormatError, RealtimeProviderError, RealtimeReadTimeout. Routed to the auto-injected streaming-errors sink so provider failures never block the voice loop.

Canonical error_typeErrorFrame substrateVoice loop never blocks

Built on

Real services. Your stack.

Every dependency is a registered Strongly service or a model you control. Swap any one of them in the install wizard. The graph stays intact.

Realtime node

streaming-realtime-agent 1.0.0 - aiohttp WebSocket through the AI Gateway

Realtime model

OpenAI Realtime (gpt-4o-realtime-preview) by default; Gemini Live also supported

Recorder

streaming-recorder 1.4.0 - audio.wav + transcript.json + manifest.json + spans.json on EndFrame

Strongly tracing

Per-frame spans on workflow_spans (Mongo) - same path as the batch runtime

Five common customisations

Tune it. Don't fork it.

The marketplace template is the graph. Every customisation below is a config change or a single-node addition - never a rewrite.

Voice swap

Edit rt.config.voice or send a SteerFrame mid-session. Voice swaps defer until the current response finishes.

Different system prompt

rt.config.system_prompt sets the initial instructions. Use SteerFrame.instructions for runtime mutations.

Audio-only modality

Set rt.config.modalities to audio to skip transcript-delta emission and save tokens.

Tighter audio formats

Default is pcm16_16k on both sides. Switch to pcm16_24k for higher fidelity, or g711_mulaw for telephony bridges.

Provider param overrides

rt.config.provider_param_overrides is a dict merged into the initial session.update for OpenAI-Realtime-specific knobs (max_response_output_tokens, etc.).