Cloudflare 推出实时语音 AI 平台：Realtime Agents

RealtimeAgent

export class MyAgent extends RealtimeAgent<Env> {
	constructor(ctx: DurableObjectState, env: Env) {
		super(ctx, env);
	}

	async init(agentId: string ,meetingId: string, authToken: string, workerUrl: string, accountId: string, apiToken: string) {
		// Construct your text processor for generating responses to text
		const textHandler = new MyTextHandler(this.env);
		// Construct a Meeting object to join the RTK meeting
		const transport = new RealtimeKitTransport(meetingId, authToken, [
			{
				media_kind: 'audio',
				stream_kind: 'microphone',
			},
		]);
		const { meeting } = transport;

		// Construct a pipeline to take in meeting audio, transcribe it using
		// Deepgram, and pass our generated responses through ElevenLabs to
		// be spoken in the meeting
		await this.initPipeline(
			[transport, new DeepgramSTT(this.env.DEEPGRAM_API_KEY), textHandler, new ElevenLabsTTS(this.env.ELEVENLABS_API_KEY), transport],
			agentId,
			workerUrl,
			accountId,
			apiToken,
		);

		// The RTK meeting object is accessible to us, so we can register handlers
		// on various events like participant joins/leaves, chat, etc.
		// This is optional
		meeting.participants.joined.on('participantJoined', (participant) => {
			textHandler.speak(`Participant Joined ${participant.name}`);
		});
		meeting.participants.joined.on('participantLeft', (participant) => {
			textHandler.speak(`Participant Left ${participant.name}`);
		});

		// Make sure to actually join the meeting after registering all handlers
		await meeting.rtkMeeting.join();
	}

	async deinit() {
		// Add any other cleanup logic required
		await this.deinitPipeline();
	}
}