voice-agents by casper-studios/casper-marketplace
npx skills add https://github.com/casper-studios/casper-marketplace --skill voice-agents为客户的发现、反馈和跟进通话创建 ElevenLabs 对话式 AI 语音助手。根据客户上下文自动生成助手配置。
What type of agent?
│
├── Discovery agent (interview clients)
│ └── --scope discovery
│
├── Feedback agent (post-project)
│ └── --scope feedback
│
├── Check-in agent (relationship)
│ └── --scope check-in
│
├── Qualification agent (leads)
│ └── --scope qualification
│
└── Onboarding agent (new contacts)
└── --scope onboarding
# 在 .env 文件中必需
ELEVENLABS_API_KEY=your_api_key
OPENROUTER_API_KEY=your_api_key # 用于提示生成
python scripts/create_voice_agent.py "Microsoft" --scope discovery --notes "CRM migration project"
python scripts/create_voice_agent.py "Acme Corp" --scope feedback --notes "Post-project review"
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
python scripts/create_voice_agent.py "Test Company" --scope discovery --notes "Testing" --dry-run
| 范围 | 用途 |
|---|---|
discovery | 采访客户团队关于运营、痛点、技术栈 |
feedback | 收集已完成项目的反馈 |
check-in | 定期关系跟进 |
qualification | 在销售前筛选入站线索 |
onboarding | 引导新联系人完成信息收集 |
脚本生成:
[{公司名称}] {范围} 助手 v1
为语音优化的问候语,包含:
全面的对话指南,包含:
{
"agent_id": "abc123xyz",
"agent_name": "[Microsoft] Discovery Agent v1",
"agent_url": "https://elevenlabs.io/app/conversational-ai/agents/abc123xyz",
"first_message": "Hi there! This is an AI assistant...",
"company_name": "Microsoft",
"scope": "discovery"
}
脚本可选择性地从 Google Drive 获取上下文:
如果不可用,则仅使用提供的备注生成。
| 服务 | 成本 |
|---|---|
| OpenRouter(提示生成) | ~$0.01-0.03 |
| ElevenLabs 助手创建 | 免费 |
| Google Drive | 免费 |
ELEVENLABS_API_KEY 存储在 .env 文件中(切勿提交到 git)OPENROUTER_API_KEY 存储在 .env 文件中(切勿提交到 git)ELEVENLABS_API_KEY - 完全访问语音助手创建/管理OPENROUTER_API_KEY - 用于提示生成的 AI 模型访问权限症状: 创建语音助手时出现 API 错误 原因: 配置无效、缺少字段或 API 问题 解决方案:
症状: “未找到语音”或“无效的 voice_id”错误 原因: 语音 ID 不存在或无法访问 解决方案:
症状: “配额超出”或速率限制错误 原因: 达到 ElevenLabs 订阅限制 解决方案:
症状: 助手已创建但在对话中不响应 原因: 系统提示问题、webhook 配置或服务问题 解决方案:
症状: 生成助手提示时出错 原因: OpenRouter API 问题或模型无效 解决方案:
OPENROUTER_API_KEY 是否正确设置--dry-run 运行以在不调用 API 的情况下进行测试症状: 创建的助手没有客户上下文 原因: OAuth 问题或未找到客户文件夹 解决方案:
--notes 标志提供上下文作为替代方案技能: transcript-search → voice-agents 用例: 创建具有客户历史记录的语音助手 流程:
技能: voice-agents → attio-crm 用例: 记录语音助手通话摘要 流程:
技能: parallel-research → voice-agents 用例: 为语音助手提供公司情报 流程:
每周安装数
91
仓库
GitHub 星标
9
首次出现
14 天前
安全审计
安装于
cline91
github-copilot91
codex91
kimi-cli91
gemini-cli91
cursor91
Create ElevenLabs Conversational AI voice agents for client discovery, feedback, and check-in calls. Automatically generates agent configuration from client context.
What type of agent?
│
├── Discovery agent (interview clients)
│ └── --scope discovery
│
├── Feedback agent (post-project)
│ └── --scope feedback
│
├── Check-in agent (relationship)
│ └── --scope check-in
│
├── Qualification agent (leads)
│ └── --scope qualification
│
└── Onboarding agent (new contacts)
└── --scope onboarding
# Required in .env
ELEVENLABS_API_KEY=your_api_key
OPENROUTER_API_KEY=your_api_key # For prompt generation
python scripts/create_voice_agent.py "Microsoft" --scope discovery --notes "CRM migration project"
python scripts/create_voice_agent.py "Acme Corp" --scope feedback --notes "Post-project review"
python scripts/create_voice_agent.py "Test Company" --scope discovery --notes "Testing" --dry-run
| Scope | Purpose |
|---|---|
discovery | Interview client team about operations, pain points, tech stack |
feedback | Gather feedback on completed project |
check-in | Periodic relationship check-ins |
qualification | Qualify inbound leads before sales |
onboarding | Guide new contacts through info gathering |
The script generates:
[{Company Name}] {Scope} Agent v1
Voice-optimized greeting that:
Comprehensive conversation guide with:
{
"agent_id": "abc123xyz",
"agent_name": "[Microsoft] Discovery Agent v1",
"agent_url": "https://elevenlabs.io/app/conversational-ai/agents/abc123xyz",
"first_message": "Hi there! This is an AI assistant...",
"company_name": "Microsoft",
"scope": "discovery"
}
The script optionally fetches context from Google Drive:
If not available, generates with provided notes only.
| Service | Cost |
|---|---|
| OpenRouter (prompt generation) | ~$0.01-0.03 |
| ElevenLabs agent creation | Free |
| Google Drive | Free |
ELEVENLABS_API_KEY in .env file (never commit to git)OPENROUTER_API_KEY in .env file (never commit to git)ELEVENLABS_API_KEY - Full access to voice agent creation/managementOPENROUTER_API_KEY - AI model access for prompt generationSymptoms: API error when creating voice agent Cause: Invalid configuration, missing fields, or API issue Solution:
Symptoms: "Voice not found" or "invalid voice_id" error Cause: Voice ID doesn't exist or not accessible Solution:
Symptoms: "Quota exceeded" or rate limit error Cause: ElevenLabs subscription limits reached Solution:
Symptoms: Agent created but doesn't respond in conversations Cause: System prompt issues, webhook configuration, or service issue Solution:
Symptoms: Error generating agent prompt Cause: OpenRouter API issue or invalid model Solution:
OPENROUTER_API_KEY is set correctly--dry-run to test without API callsSymptoms: Agent created without client context Cause: OAuth issue or client folder not found Solution:
--notes flag as alternativeSkills: transcript-search → voice-agents Use case: Create voice agents with client history Flow:
Skills: voice-agents → attio-crm Use case: Log voice agent call summaries Flow:
Skills: parallel-research → voice-agents Use case: Arm voice agents with company intelligence Flow:
Weekly Installs
91
Repository
GitHub Stars
9
First Seen
14 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
cline91
github-copilot91
codex91
kimi-cli91
gemini-cli91
cursor91
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
66,200 周安装