does it work with typescript and gemini for multim...
# ask-air
red-agent-48266
09/11/2025, 4:36 PMdoes it work with typescript and gemini for multimodal models
import { JobContext, WorkerOptions, cli, defineAgent, multimodal } from '@livekit/agents';
import * as openai from '@livekit/agents-plugin-openai';
export default defineAgent({
entry: async (ctx: JobContext) => {
await ctx.connect();
const agent = new multimodal.MultimodalAgent({
model: new openai.realtime.RealtimeModel({
instructions: "You are a helpful assistant.",
voice: 'shimmer',
modalities: ['text', 'audio'],
}),
});
await agent.start(ctx.room);
},
});
cli.runApp(new WorkerOptions({ agent: import.meta.url, workerType: JobType.JT_ROOM }));
t
tall-airline-16756
09/11/2025, 4:36 PMThanks for reaching out, Hrithik. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
tall-airline-16756
09/11/2025, 4:38 PMHi there! I wanted to share some helpful info about LiveKit and how it supports both TypeScript and Gemini for multimodal models. The code snippet you mentioned using
@livekit/agents@livekit/agents-plugin-openai@livekit/agents-plugin-googlegoogle.beta.realtime.RealtimeModel Copy code
import { defineAgent, JobContext } from '@livekit/agents';
import * as google from '@livekit/agents-plugin-google';
export default defineAgent({
entry: async (ctx: JobContext) => {
await ctx.connect();
const participant = await ctx.waitForParticipant();
const model = new google.beta.realtime.RealtimeModel({
instructions: 'You are a helpful assistant.',
});
const agent = new multimodal.MultimodalAgent({ model });
await agent.start(ctx.room, participant);
},
});