Голосовой агент

import { Agent, routeAgentRequest } from "agents";
import { withVoice, WorkersAIFluxSTT, WorkersAITTS } from "@cloudflare/voice";
import { streamText, tool, stepCountIs } from "ai";
import { createWorkersAI } from "workers-ai-provider";
import { z } from "zod";

const VoiceAgent = withVoice(Agent);

export class MyVoiceAgent extends VoiceAgent {
	transcriber = new WorkersAIFluxSTT(this.env.AI);
	tts = new WorkersAITTS(this.env.AI);

	async onTurn(transcript, context) {
		const workersAi = createWorkersAI({ binding: this.env.AI });

		const result = streamText({
			model: workersAi("@cf/moonshotai/kimi-k2.6"),
			system:
				"You are a helpful voice assistant. Keep responses concise — you are being spoken aloud.",
			messages: [
				...context.messages.map((m) => ({
					role: m.role,
					content: m.content,
				})),
				{ role: "user", content: transcript },
			],
			tools: {
				get_current_time: tool({
					description: "Get the current date and time.",
					inputSchema: z.object({}),
					execute: async () => ({
						time: new Date().toLocaleTimeString("en-US", {
							hour: "2-digit",
							minute: "2-digit",
						}),
					}),
				}),
			},
			stopWhen: stepCountIs(3),
			abortSignal: context.signal,
		});

		return result.textStream;
	}

	async onCallStart(connection) {
		await this.speak(connection, "Hi there! How can I help you today?");
	}
}

export default {
	async fetch(request, env) {
		return (
			(await routeAgentRequest(request, env)) ??
			new Response("Not found", { status: 404 })
		);
	},
};

import { Agent, routeAgentRequest, type Connection } from "agents";
import {
	withVoice,
	WorkersAIFluxSTT,
	WorkersAITTS,
	type VoiceTurnContext,
} from "@cloudflare/voice";
import { streamText, tool, stepCountIs } from "ai";
import { createWorkersAI } from "workers-ai-provider";
import { z } from "zod";

const VoiceAgent = withVoice(Agent);

export class MyVoiceAgent extends VoiceAgent<Env> {
	transcriber = new WorkersAIFluxSTT(this.env.AI);
	tts = new WorkersAITTS(this.env.AI);

	async onTurn(transcript: string, context: VoiceTurnContext) {
		const workersAi = createWorkersAI({ binding: this.env.AI });

		const result = streamText({
			model: workersAi("@cf/moonshotai/kimi-k2.6"),
			system:
				"You are a helpful voice assistant. Keep responses concise — you are being spoken aloud.",
			messages: [
				...context.messages.map((m) => ({
					role: m.role as "user" | "assistant",
					content: m.content,
				})),
				{ role: "user" as const, content: transcript },
			],
			tools: {
				get_current_time: tool({
					description: "Get the current date and time.",
					inputSchema: z.object({}),
					execute: async () => ({
						time: new Date().toLocaleTimeString("en-US", {
							hour: "2-digit",
							minute: "2-digit",
						}),
					}),
				}),
			},
			stopWhen: stepCountIs(3),
			abortSignal: context.signal,
		});

		return result.textStream;
	}

	async onCallStart(connection: Connection) {
		await this.speak(connection, "Hi there! How can I help you today?");
	}
}

export default {
	async fetch(request: Request, env: Env) {
		return (
			(await routeAgentRequest(request, env)) ??
			new Response("Not found", { status: 404 })
		);
	},
} satisfies ExportedHandler<Env>;

export class MyVoiceAgent extends VoiceAgent {
	transcriber = new WorkersAIFluxSTT(this.env.AI);
	tts = new WorkersAITTS(this.env.AI);

	afterTranscribe(transcript, connection) {
		if (transcript.length < 3) return null;
		return transcript;
	}

	beforeSynthesize(text, connection) {
		return text.replace(/\bAI\b/g, "A.I.");
	}

	async onTurn(transcript, context) {
		return "You said: " + transcript;
	}
}

export class MyVoiceAgent extends VoiceAgent<Env> {
	transcriber = new WorkersAIFluxSTT(this.env.AI);
	tts = new WorkersAITTS(this.env.AI);

	afterTranscribe(transcript: string, connection: Connection) {
		if (transcript.length < 3) return null;
		return transcript;
	}

	beforeSynthesize(text: string, connection: Connection) {
		return text.replace(/\bAI\b/g, "A.I.");
	}

	async onTurn(transcript: string, context: VoiceTurnContext) {
		return "You said: " + transcript;
	}
}

import { ElevenLabsTTS } from "@cloudflare/voice-elevenlabs";
import { DeepgramSTT } from "@cloudflare/voice-deepgram";

export class MyVoiceAgent extends VoiceAgent {
	transcriber = new DeepgramSTT({
		apiKey: this.env.DEEPGRAM_API_KEY,
	});

	tts = new ElevenLabsTTS({
		apiKey: this.env.ELEVENLABS_API_KEY,
		voiceId: "21m00Tcm4TlvDq8ikWAM",
	});

	async onTurn(transcript, context) {
		return "You said: " + transcript;
	}
}

import { ElevenLabsTTS } from "@cloudflare/voice-elevenlabs";
import { DeepgramSTT } from "@cloudflare/voice-deepgram";

export class MyVoiceAgent extends VoiceAgent<Env> {
	transcriber = new DeepgramSTT({
		apiKey: this.env.DEEPGRAM_API_KEY,
	});

	tts = new ElevenLabsTTS({
		apiKey: this.env.ELEVENLABS_API_KEY,
		voiceId: "21m00Tcm4TlvDq8ikWAM",
	});

	async onTurn(transcript: string, context: VoiceTurnContext) {
		return "You said: " + transcript;
	}
}