Twilio Conversational Intelligence と Functions で通話録音を自動文字起こししてサマリと感情分析を取得してみた

exports.handler = function (context, event, callback) {
  const twiml = new Twilio.twiml.VoiceResponse();

  // 録音完了後にもう一度呼ばれると RecordingSid が付与される
  if (event.RecordingSid) {
    // 2 回目の呼び出しでは、お礼だけ伝えて通話を切る
    twiml.say(
      {
        language: "ja-JP",
        voice: "woman",
      },
      "ありがとうございました。"
    );
    twiml.hangup();
  } else {
    // 1 回目の呼び出しでは、ガイダンスを流して録音を開始する
    twiml.say(
      {
        language: "ja-JP",
      },
      "ピーという音のあとに話してください。"
    );

    twiml.record({
      // 録音が完了したら /ci-create-transcript（後述）へコールバックする
      recordingStatusCallback: context.RECORDING_STATUS_URL,
      recordingStatusCallbackEvent: ["completed"],
      recordingChannels: "dual",
      timeout: 5,
      maxLength: 120,
      playBeep: true,
    });
  }

  return callback(null, twiml);
};

exports.handler = async function (context, event, callback) {
  const client = context.getTwilioClient();

  // Voice の recordingStatusCallback から渡される値
  const recordingSid = event.RecordingSid; // 例: REXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
  const callSid = event.CallSid;

  console.log("RecordingSid:", recordingSid, "CallSid:", callSid);

  try {
    const transcript = await client.intelligence.v2.transcripts.create({
      serviceSid: context.INTELLIGENCE_SERVICE_SID,
      channel: {
        media_properties: {
          // Twilio Recording を Conversational Intelligence に渡す
          source_sid: recordingSid,
        },
      },
      // 後から検索しやすいように、任意のキーを付けておく
      customerKey: callSid,
    });

    console.log("Queued transcript:", transcript.sid, "status:", transcript.status);

    // Twilio Function としては空のレスポンスを返せば十分です
    return callback(null, {});
  } catch (err) {
    console.error("Failed to create transcript", err);
    return callback(err);
  }
};

exports.handler = async function (context, event, callback) {
  const eventType = event.event_type;

  // Transcript が完了すると、voice_intelligence_transcript_available が飛んでくる
  if (eventType === "voice_intelligence_transcript_available") {
    console.log("[CI] Transcript available.");
    console.log("  TranscriptSid:", event.transcript_sid);
    console.log("  CustomerKey  :", event.customer_key);
    return callback(null, { ok: true });
  }

  console.log("[CI] Unhandled event_type:", eventType);
  return callback(null, { ok: true });
};

require("dotenv").config();

const twilio = require("twilio");

const accountSid = process.env.TWILIO_ACCOUNT_SID;
const authToken = process.env.TWILIO_AUTH_TOKEN;
const transcriptSid = process.env.TRANSCRIPT_SID;  // 先ほどの TranscriptSid をここに設定

if (!accountSid || !authToken) {
  console.error("TWILIO_ACCOUNT_SID / TWILIO_AUTH_TOKEN が設定されていません。");
  process.exit(1);
}

const client = twilio(accountSid, authToken);

async function main() {
  console.log("Target TranscriptSid:", transcriptSid);

  // まず Transcript 自体の概要を確認
  try {
    const transcript = await client.intelligence.v2
      .transcripts(transcriptSid)
      .fetch();

    console.log("=== Transcript info ===");
    console.log("sid:", transcript.sid);
    console.log("status:", transcript.status);
    console.log("customerKey:", transcript.customerKey);
    console.log("serviceSid:", transcript.serviceSid);
    console.log("url:", transcript.url);
  } catch (err) {
    console.error("Failed to fetch transcript:", err);
    process.exit(1);
  }

  // 次に OperatorResults 一式を取得して 1 行ずつ出力
  try {
    const operatorResults = await client.intelligence.v2
      .transcripts(transcriptSid)
      .operatorResults.list({ limit: 20 });

    console.log("OperatorResults count:", operatorResults.length);

    operatorResults.forEach((r, i) => {
      console.log(`\n--- OperatorResult[${i}] ---`);
      console.log("operatorType:", r.operatorType);
      console.log("name:", r.name);
      console.log("operatorSid:", r.operatorSid);

      console.log("extractMatch:", r.extractMatch);
      console.log("matchProbability:", r.matchProbability);
      console.log("normalizedResult:", r.normalizedResult);
      console.log("utteranceMatch:", r.utteranceMatch);

      console.log("predictedLabel:", r.predictedLabel);
      console.log("predictedProbability:", r.predictedProbability);

      console.log(
        "labelProbabilities:",
        r.labelProbabilities
          ? JSON.stringify(r.labelProbabilities, null, 2)
          : r.labelProbabilities
      );

      console.log(
        "extractResults:",
        r.extractResults
          ? JSON.stringify(r.extractResults, null, 2)
          : r.extractResults
      );

      console.log(
        "utteranceResults:",
        r.utteranceResults
          ? JSON.stringify(r.utteranceResults, null, 2)
          : r.utteranceResults
      );

      console.log(
        "textGenerationResults:",
        r.textGenerationResults
          ? JSON.stringify(r.textGenerationResults, null, 2)
          : r.textGenerationResults
      );

      console.log(
        "jsonResults:",
        r.jsonResults ? JSON.stringify(r.jsonResults, null, 2) : r.jsonResults
      );

      console.log("transcriptSid:", r.transcriptSid);
      console.log("url:", r.url);
    });
  } catch (err) {
    console.error("Failed to fetch operator results:", err);
    process.exit(1);
  }
}

main();

Target TranscriptSid: GT****
=== Transcript info ===
sid: GT****
status: completed
customerKey: CA****
serviceSid: GA****
url: https://intelligence.twilio.com/v2/Transcripts/GT****
OperatorResults count: 3

--- OperatorResult[0] ---
operatorType: json
name: test-operator
operatorSid: LY****
extractMatch: null
matchProbability: null
normalizedResult: null
utteranceMatch: null
predictedLabel: null
predictedProbability: null
labelProbabilities: {}
extractResults: {}
utteranceResults: []
textGenerationResults: null
jsonResults: {
  "category": "other",
  "emotion": "negative"
}
transcriptSid: GT****
url: https://intelligence.twilio.com/v2/Transcripts/GT****/OperatorResults/LY****

--- OperatorResult[1] ---
operatorType: text-generation
name: Conversation Summary
operatorSid: LY****
extractMatch: null
matchProbability: null
normalizedResult: null
utteranceMatch: null
predictedLabel: null
predictedProbability: null
labelProbabilities: {}
extractResults: {}
utteranceResults: []
textGenerationResults: {
  "format": "text",
  "result": "The customer is experiencing issues logging into their account. The call center agent informs the customer that they are unable to access the account system. The conversation revolves around troubleshooting the login problem."
}
jsonResults: null
transcriptSid: GT****
url: https://intelligence.twilio.com/v2/Transcripts/GT****/OperatorResults/LY****

--- OperatorResult[2] ---
operatorType: conversation-classify
name: Sentiment Analysis
operatorSid: LY****
extractMatch: null
matchProbability: null
normalizedResult: null
utteranceMatch: null
predictedLabel: neutral
predictedProbability: 1.0
labelProbabilities: {
  "neutral": 1
}
extractResults: {}
utteranceResults: []
textGenerationResults: null
jsonResults: null
transcriptSid: GT****
url: https://intelligence.twilio.com/v2/Transcripts/GT****/OperatorResults/LY****