Member Junction
    Preparing search index...
    • Builds the configOverridesJson payload for the StartRealtimeClientSession mint from what the (authorization-gated) pickers chose — an explicit realtime model preference and/or a voice. The envelope ({"realtime":{"modelPreference":"<id>","voice":{"default":{"voice":"<v>"}}}}) is the pinned server contract, merged into the effective config server-side (highest precedence).

      The voice is filed PROVIDER-AGNOSTICALLY: the browser has a model id, never a vendor DriverClass (GetRealtimeModelVoices does not return one), so naming a provider here would be a guess that silently voided the setting for every non-OpenAI vendor. The server files it onto whichever driver it resolves. Kept in lockstep with the server-side BuildRealtimeOverridesJson in @memberjunction/ai-agents by realtime-convergence-drift.test.ts. See issue #3530.

      Parameters

      • preferredModelId: string | null | undefined

        The explicit MJ: AI Models id, or null/empty for none.

      • OptionalpreferredVoice: string | null

        The provider-native voice id (e.g. echo), or null/empty for none.

      Returns string | null

      The JSON string, or null when nothing was overridden (keeps the mint identical to default).