Class BaseRealtimeModelAbstract

constructor

• new BaseRealtimeModel(apiKey: string): BaseRealtimeModel

  Parameters

  • apiKey: string

  Returns BaseRealtimeModel

Static Optional ReadonlySupportsDynamicToolSet

SupportedVoices

• get SupportedVoices(): RealtimeVoiceOption[]

  Static fallback list of provider-native voices supported by this driver when metadata personas are not present or sparse.

  NOTE: Database metadata (MJ: AI Personas + AI Model Personas) is authoritative where configured. At runtime, GetRealtimeModelVoices unions metadata personas with this driver fallback list so that newly uncatalogued provider voices remain selectable while catalogued personas carry curated names/descriptions.

  Returns RealtimeVoiceOption[]

  The supported voice ids (id + human label), or [] when none are declared.

SupportsClientDirect

• get SupportsClientDirect(): boolean

  Whether this driver can mint an ephemeral, server-scoped client credential for a client-direct realtime session (the browser opens its own provider socket using a short-lived token the server minted).

  Defaults to false. Providers that support browser-direct sessions override this to true and implement CreateClientSession. The server-bridged topology (where the provider socket lives on the server, via StartSession) is supported by every driver regardless of this flag.

  Returns boolean

  true if CreateClientSession is supported; false otherwise.

SupportsVideo

• get SupportsVideo(): boolean

  Whether this driver's sessions carry a video track in addition to audio.

  Returns boolean

  false in every MJ driver.

  Deprecated

  Nothing reads it, and no driver overrides it: it is false for Gemini Live, which takes camera video and renders avatars. What a session does with video is declared on its IRealtimeSession.Capabilities: RealtimeSessionCapabilities.SupportedInboundTracks for video in and RealtimeSessionCapabilities.SupportedOutboundTracks for video out, each track with its encoding. Whether a model renders a live avatar is SupportsAvatarOutput. A driver declares video there, not here.

CreateClientSession

• CreateClientSession(
      _params: RealtimeSessionParams,
  ): Promise<ClientRealtimeSessionConfig>

  Mints an ephemeral, server-scoped client credential plus a provider-native session config for a client-direct realtime session.

  In the client-direct topology the browser owns the provider socket (e.g. WebRTC), but the server still controls the prompt and tool set: it mints a short-lived token and hands back a ClientRealtimeSessionConfig whose SessionConfig the matching client driver applies when it opens its socket. This keeps prompt/tool authority server-side even though the media plane is client-direct.

  Not every provider supports this (some only expose a server-bridged socket), so this is a concrete method that throws by default rather than an abstract one — that would force every existing and future driver to implement it. Providers that support it override SupportsClientDirect to true and override this method.

  Parameters

  • _params: RealtimeSessionParams

    The session parameters (system prompt, tools, model, config bag).

  Returns Promise<ClientRealtimeSessionConfig>

  A promise resolving to the minted ClientRealtimeSessionConfig.

  Throws

  Always, unless overridden by a provider that supports client-direct sessions.

OptionalExchangeWebRtcSdp

• ExchangeWebRtcSdp?(
      _offerSdp: string,
      _sessionConfig?: Record<string, unknown>,
  ): Promise<{ answerSdp: string; prebillSeconds: number; sessionId: string }>

  Optional WebRTC SDP exchange seam for drivers that support server-brokered WebRTC topologies.

  Parameters

  • _offerSdp: string

    The local SDP offer generated by the browser.

  • Optional_sessionConfig: Record<string, unknown>

    The session configuration to initialize the session with.

  Returns Promise<{ answerSdp: string; prebillSeconds: number; sessionId: string }>

  The answer SDP, provider session ID, and any prebill accounting.

AbstractStartSession

• StartSession(params: RealtimeSessionParams): Promise<IRealtimeSession>

  Opens a stateful duplex session with the provider.

  The returned IRealtimeSession is the long-lived handle that streams media and transcripts in both directions, surfaces tool calls and usage telemetry, and reports provider-detected interruptions (barge-in). The caller is responsible for closing the session via IRealtimeSession.Close.

  Parameters

  • params: RealtimeSessionParams

    Configuration for the session (system prompt, tools, initial context, model, and an open config bag).

  Returns Promise<IRealtimeSession>

  A promise resolving to the live session handle.

SupportsAvatarOutput

• SupportsAvatarOutput(_model: string): boolean

  Whether this driver's sessions can render a live avatar for the model, on the endpoint the driver serves.

  Defaults to false: a driver whose models render no avatar says nothing more, and may ignore an avatar request. A driver that renders one for some models (Gemini Enterprise) overrides it. The client-session service reads it to tell a call or a meeting that asked for an avatar "this voice model can't show an avatar" (RealtimeAvatarUnavailableReason 'endpoint'), whichever driver serves it.

  Parameters

  • _model: string

    The provider's API name for the model.

  Returns boolean

  true when sessions on this model can render a live avatar; false otherwise.