销售通话 AI 分析：Whisper 转录 + GPT-4o 生成洞察并同步 Airtable 与 Slack

销售代表提交通话录音链接 → n8n 自动下载音频、Whisper 转文字、GPT-4o 分析情绪与异议 → 结果写入 Airtable、通知 Slack、并返回 HTML 报告页

给谁

销售团队、RevOps 经理与销售教练，希望自动获得每通销售通话的结构化洞察，无需人工逐条回听

你会得到

提交录音后自动获得：情绪评分、异议清单（附原文引用）、购买信号、阶段建议、教练建议、CRM 备注与跟进邮件草稿，同时入库 Airtable 并通知 Slack

你需要

n8n · airtable · slack

步骤

1. 准备凭证与表单：配置 OpenAI、Airtable、Slack 并启用工作流

   在 n8n 中依次完成以下配置： 1. 打开「4. OpenAI — Transcribe with Whisper」节点，将 Authorization header 中的 YOUR_TOKEN_HERE 替换为 OpenAI API 密钥（建议创建 n8n Header Auth 凭证并引用，不要硬编码）。来源说明文字（description.md）此处写 YOUR_OPENAI_API_KEY，但 workflow.json 实际节点参数为 YOUR_TOKEN_HERE；以下以节点实际值为准。 2. 进入 Credentials → 添加 OpenAI API 凭证 → 在「7. OpenAI — Chat Model (GPT-4o)」节点选择该凭证。 3. 添加 Airtable Personal Access Token 凭证 → 在「9. Airtable — Save Full Analysis」节点选择 Base 与 Table。Table 必须包含以下 26 列（名称需完全匹配，含空格与大小写）：Submission ID、Rep Name、Rep Email、Company、Contact Name、Contact Email、Deal Stage (Before)、Deal Stage (AI Recommended)、Deal Value、Call Duration (min)、Word Count、Sentiment、Sentiment Score、Primary Intent、Deal Risk、Deal Momentum、Objection Count、Buying Signal Count、Competitors Mentioned、Summary、CRM Note、Coaching Tip、Rep Talk Ratio、Follow-up Email Draft、Submitted At、Processed At。 4. 在 Slack 创建 App 并启用 Incoming Webhook → 复制 Webhook URL → 在 n8n Credentials 添加 Slack Webhook 凭证 → 在「10. Slack — Post Analysis to Channel」节点选择该凭证。 5. 点击工作流顶部开关激活工作流，复制「1. Form — Sales Rep Submits Call」节点的表单 URL 分享给销售团队。 销售代表通过表单提交：姓名、邮箱、客户公司、联系人、当前阶段、预估金额、通话录音直链（mp3/wav/m4a）。通话时长（Call Duration）与备注（Any notes before analysis?）为可选字段。

2. 下载音频并用 Whisper 转录为文字

   工作流通过 HTTP Request 节点下载表单提交的音频直链（超时 60 秒，continueOnFail: true），随后调用 OpenAI Whisper API（model=whisper-1, response_format=verbose_json, language=en，超时 180 秒，continueOnFail: true）将音频转为带时间戳的完整文本。若音频为空或损坏，后续节点会报错终止。

3. 合并转录文本与通话元数据

   Code 节点将 Whisper 返回的 transcript 与原始表单数据合并，计算字数（wordCount），生成统一的数据对象供下一步 AI 分析使用。若转录结果为空，抛出错误提示音频可能无声或已损坏。

4. GPT-4o 销售分析：生成结构化 JSON 洞察

   AI Agent 节点将完整转录文本与通话元数据传给 GPT-4o，通过系统提示词要求模型返回严格的单一 JSON 对象，包含：摘要、情绪与评分、主要意图、风险等级、推进势头、建议阶段、代表讲话比例、异议清单（附原文引用）、购买信号、竞品提及、下一步行动（含负责人与截止日期）、教练建议、CRM 备注、跟进邮件草稿。提示词明确要求：仅输出 JSON、不包裹 markdown 代码块、未提及内容用空数组或 null、禁止编造。

   运行提示词 · 来源原文。「6. AI Agent — GPT-4o Sales Analysis」节点的 text 参数（系统提示词）

   复制提示词

   =You are an expert sales call analyst. You will receive a sales call transcript along with call metadata. Your job is to analyze the transcript deeply and return a single valid JSON object — nothing else. No explanation, no markdown, no code fences. Only raw JSON.
   
   ---
   
   INPUT YOU WILL RECEIVE:
   - repName: Name of the sales rep
   - company: Prospect company name
   - contactName: Prospect contact person
   - dealStage: Current deal stage (e.g. Discovery, Demo, Proposal)
   - dealValue: Estimated deal value in USD
   - durationMins: Call duration in minutes
   - repNotes: Any notes added by the rep before analysis
   - transcript: Full text transcript of the sales call
   
   ---
   
   YOUR JOB:
   Carefully read the transcript and return this exact JSON structure:
   
   {
     "summary": "A clear 3–5 sentence summary of what happened on this call. What was discussed, what the prospect said, and how the call ended.",
   
     "overall_sentiment": "Positive | Neutral | Negative",
   
     "sentiment_score": A number from 0 to 100. 0 = very negative, 100 = very positive.,
   
     "primary_intent": "One short phrase describing what the prospect mainly wants. Example: 'Evaluating alternatives to current tool' or 'Ready to buy pending legal approval'",
   
     "deal_risk": "Low | Medium | High",
   
     "deal_momentum": "Accelerating | Steady | Stalling | Declining",
   
     "recommended_stage": "The deal stage you recommend AFTER this call. Choose from: Prospecting, Discovery, Demo, Proposal, Negotiation, Closed Won, Closed Lost",
   
     "rep_talk_ratio": "Estimate of how much the rep talked vs the prospect. Example: '65% rep / 35% prospect'",
   
     "objections": [
       {
         "type": "Price | Timeline | Competition | Authority | Need | Other",
         "quote": "A short direct quote from the transcript showing this objection",
         "was_addressed": true or false
       }
     ],
   
     "buying_signals": [
       "List each buying signal as a short sentence. Example: 'Prospect asked about onboarding timeline' or 'Prospect mentioned they have budget approved'"
     ],
   
     "competitors_mentioned": [
       "List any competitor names mentioned on the call. Empty array if none."
     ],
   
     "next_steps": [
       {
         "action": "What needs to happen next",
         "owner": "rep | prospect | both",
         "commitment": "Was this committed to on the call? yes or no",
         "deadline": "Deadline if mentioned, otherwise null"
       }
     ],
   
     "coaching_tip": "One specific, actionable coaching tip for the rep based on this call. Be direct and helpful. Example: 'You spoke for 70% of the call — on the next call, ask more open-ended questions and let the prospect lead.'",
   
     "crm_note": "A 2–3 sentence CRM note ready to paste into a CRM. Professional tone. Include deal stage, key outcomes, and next steps.",
   
     "follow_up_email": "A ready-to-send follow-up email from the rep to the prospect. Include subject line at the top like 'Subject: ...'. Keep it professional, warm, and under 150 words. Reference something specific from the call."
   }
   
   ---
   
   STRICT RULES:
   1. Output ONLY the JSON object above. No text before or after it.
   2. Do not wrap in markdown code blocks or backticks.
   3. If something is not mentioned in the transcript, use an empty array [] or null — do not guess or hallucinate.
   4. Quotes in the "objections" field must come directly from the transcript.
   5. The follow_up_email must feel personal — reference something the prospect actually said.
   6. Keep all text in English unless the transcript is in another language.

5. 解析 GPT-4o 输出并合并为完整记录

   Code 节点清理 GPT-4o 返回文本中的 markdown 代码块标记，解析为 JSON，与原始通话数据合并，并添加 processedAt 时间戳。若解析失败，错误信息会包含原始输出的前 300 个字符以便排查。

6. 并行交付：写入 Airtable、通知 Slack、返回 HTML 报告页

   完整记录同时分发到三个渠道： - Airtable：创建新行，填充全部 26 个字段（continueOnFail: true）； - Slack：向销售频道发送分析摘要通知（continueOnFail: true）； - HTML 页面：Code 节点构建包含摘要、情绪评分、异议、下一步、教练建议与跟进邮件的格式化页面，通过「12. Webhook — Show Results Page to Rep」节点直接返回给销售代表作为表单提交确认页。 HTTP 下载节点、Whisper 节点、Airtable 节点与 Slack 节点均设置 continueOnFail: true，确保即使部分步骤失败，代表仍能看到 HTML 结果页。工作流使用 responseMode: lastNode，表单会等待最终 Webhook 响应节点完成后才向代表展示页面。

你正在搭建一个 n8n 工作流：销售代表提交通话录音后，自动获得 AI 分析报告。我已提供完整的节点配置说明、GPT-4o 系统提示词原文、Airtable 列名清单与表单字段定义。请先确认你已具备：n8n 实例、OpenAI API 密钥、Airtable Personal Access Token、Slack Incoming Webhook。然后按步骤逐一核对凭证与节点参数，不要直接运行。