Connect Agora to Smallest AI Voice Models

Set Smallest AI as the ASR and TTS provider in Agora's Conversational AI Engine. Vendors are declared in the agent's join config, so switching is a configuration change, not a code change.

OVERVIEW

Real-time speech, declared in your config.

Agora's Conversational AI Engine is a managed pipeline for building real-time voice agents over RTC, wiring together transport, ASR, LLM, and TTS. This integration sets Smallest AI as both the speech-to-text and text-to-speech vendor, so your agent listens with Pulse and speaks with Lightning. Because vendors are selected declaratively in the agent's join request, pointing Agora at Smallest AI means editing configuration rather than writing code. You set the vendor to smallestai on both the asr and tts legs of the join config, add your API key, and pick a Lightning model and voice. Interruptions are handled by the engine itself: when a caller speaks over the agent, the TTS leg is flushed and Lightning synthesis is cancelled mid-stream.

HOW IT WORKS

Up and running in four steps.

Step 1 illustration