与雕像对话：构建多模态 ElevenAgents 驱动的应用

We need to make an app that:
- is optimised for mobile
- allows the user to take a picture (of a statue, picture, monument, etc) that includes one or more people
- uses an OpenAI LLM api call to identify the statue/monument/picture, characters within it, the location, and name
- allows the user to check it's correct, and then do either a deep research or a standard search to get information about the characters and the statue's history, and it's current location
- then create an ElevenLabs agent (allowing multiple voices), that the user can then talk to as though they're talking to the characters in the statue. Each character should use voice designer api to create a matching voice.
The purpose is to be fun and educational.

https://elevenlabs.io/docs/eleven-api/guides/how-to/voices/voice-design
https://elevenlabs.io/docs/eleven-agents/quickstart 
https://elevenlabs.io/docs/api-reference/agents/create

{
  "statueName": "string - name of the statue, monument, or artwork",
  "location": "string - where it is located (city, country)",
  "artist": "string - the creator of the artwork",
  "year": "string - year completed or unveiled",
  "description": "string - brief description of the artwork and its historical significance",
  "characters": [
    {
      "name": "string - character name",
      "description": "string - who this person was and their historical significance",
      "era": "string - time period they lived in",
      "voiceDescription": "string - detailed voice description for Voice Design API (include audio quality marker, age, gender, vocal qualities, accent, pacing, and personality)"
    }
  ]
}

const response = await openai.chat.completions.create({
  model: "gpt-5.2",
  response_format: { type: "json_object" },
  messages: [
    { role: "system", content: SYSTEM_PROMPT },
    {
      role: "user",
      content: [
        {
          type: "text",
          text: "Identify this statue/monument/artwork and all characters depicted.",
        },
        {
          type: "image_url",
          image_url: {
            url: `data:image/jpeg;base64,${base64Data}`,
            detail: "high",
          },
        },
      ],
    },
  ],
  max_completion_tokens: 2500,
});

{
  "statueName": "Boudica and Her Daughters",
  "location": "Westminster Bridge, London, UK",
  "artist": "Thomas Thornycroft",
  "year": "1902",
  "description": "Bronze statue depicting Queen Boudica riding a war chariot with her two daughters, commemorating her uprising against Roman occupation of Britain.",
  "characters": [
    {
      "name": "Boudica",
      "description": "Queen of the Iceni tribe who led an uprising against Roman occupation",
      "era": "Ancient Britain, 60-61 AD",
      "voiceDescription": "Perfect audio quality. A powerful woman in her 30s with a deep, resonant voice and a thick Celtic British accent. Her tone is commanding and fierce, with a booming quality that projects authority. She speaks at a measured, deliberate pace with passionate intensity."
    },
    // Other characters in the statue
  ]
}

const { previews } = await elevenlabs.textToVoice.design({
  modelId: "eleven_multilingual_ttv_v2",
  voiceDescription: character.voiceDescription,
  text: sampleText,
});

const voice = await elevenlabs.textToVoice.create({
  voiceName: `StatueScanner - ${character.name}`,
  voiceDescription: character.voiceDescription,
  generatedVoiceId: previews[0].generatedVoiceId,
});

const results = await Promise.all(
  characters.map((character) => createVoiceForCharacter(character))
);

const agent = await elevenlabs.conversationalAi.agents.create({
  name: `Statue Scanner - ${statueName}`,
  tags: ["statue-scanner"],
  conversationConfig: {
    agent: {
      firstMessage,
      language: "en",
      prompt: {
        prompt: systemPrompt,
        temperature: 0.7,
      },
    },
    tts: {
      voiceId: primaryCharacter.voiceId,
      modelId: "eleven_v3",
      supportedVoices: otherCharacters.map((c) => ({
        voiceId: c.voiceId,
        label: c.name,
        description: c.voiceDescription,
      })),
    },
    turn: {
      turnTimeout: 10,
    },
    conversation: {
      maxDurationSeconds: 600,
    },
  },
});

const multiCharacterRules = `
MULTI-CHARACTER DYNAMICS:
You are playing ALL ${characters.length} characters simultaneously.
Make this feel like a group conversation, not an interview.

- Characters should interrupt each other:
  "Actually, if I may -" / "Wait, I must say -"

- React to what others say:
  "Well said." / "I disagree with that..." / "Always so modest..."

- Have side conversations:
  "Do you remember when -" / "Tell them about the time you -"

The goal is for users to feel like they are witnessing a real exchange
between people who happen to include them.
`;

const { token } = await client.conversationalAi.conversations.getWebrtcToken({
    agentId,
});

import { useConversation } from "@elevenlabs/react";

const conversation = useConversation({
  onConnect: () => setIsSessionActive(true),
  onDisconnect: () => setIsSessionActive(false),
  onMessage: (message) => {
    if (message.source === "ai") {
      setMessages((prev) => [...prev, { role: "agent", text: message.message }]);
    }
  },
});

await conversation.startSession({
  agentId,
  conversationToken: token,
  connectionType: "webrtc",
});

const response = await openai.responses.create({
  model: "gpt-5.2",
  instructions: RESEARCH_SYSTEM_PROMPT,
  tools: [{ type: "web_search_preview" }],
  input: `Research ${identification.statueName}. Search for current information
including location, visiting hours, and recent news about the artwork.`,
});