Transform voice notes into actionable sales data. Automatically transcribe, analyze, and sync to your CRM.
Field Intel helps sales reps eliminate hours of manual data entry by turning voice notes into structured CRM data. After each client conversation, reps simply record their thoughts - the app instantly transcribes, analyzes, and pushes structured data directly into your existing CRM.
- Voice Recording: Capture meeting notes on the go with our intuitive voice recorder
- AI Transcription: Automatic speech-to-text conversion with high accuracy
- Sentiment Analysis: Understand the emotional tone of conversations
- BANT Analysis: Automatic extraction of Budget, Authority, Need, and Timeline signals
- Action Items: AI-powered extraction of follow-up tasks with priorities
- CRM Integration: Seamless sync with Salesforce, HubSpot, and Pipedrive
- Real-time Dashboard: Track your sales activities and insights
- 5-50 person sales teams
- Field sales representatives
- Sales managers and directors
- Companies using Salesforce, HubSpot, or Pipedrive
- Framework: Next.js 15
- Language: TypeScript
- Styling: Tailwind CSS v4
- UI Components: shadcn/ui
- Icons: Lucide React
- Date Handling: date-fns
- Node.js 18+
- npm or yarn
- Clone the repository:
git clone <repository-url>
cd yappnotes- Install dependencies:
npm install- Run the development server:
npm run dev- Open http://localhost:3000 in your browser
npm run build
npm startyappnotes/
├── app/ # Next.js app directory
│ ├── layout.tsx # Root layout
│ ├── page.tsx # Main dashboard page
│ └── globals.css # Global styles
├── components/
│ ├── ui/ # shadcn/ui components
│ │ ├── button.tsx
│ │ ├── card.tsx
│ │ ├── input.tsx
│ │ ├── tabs.tsx
│ │ ├── badge.tsx
│ │ └── dialog.tsx
│ ├── dashboard/ # Dashboard components
│ │ ├── stats-overview.tsx
│ │ ├── recent-notes.tsx
│ │ └── note-detail.tsx
│ └── voice-recorder.tsx # Voice recording component
├── lib/
│ ├── types.ts # TypeScript type definitions
│ ├── mock-data.ts # Mock data for demo
│ ├── utils.ts # Utility functions
│ └── services/ # Service layer
│ ├── transcription.ts # Audio transcription service
│ ├── ai-analysis.ts # AI analysis service
│ └── crm-integration.ts # CRM integration service
└── public/ # Static assets
- Browser-based audio capture using Web Audio API
- Real-time audio level visualization
- Recording time tracker
- High-quality audio encoding
The app analyzes voice notes to extract:
- Sentiment: Positive, neutral, or negative tone with confidence scores
- Buying Signals: BANT framework analysis
- Budget indicators
- Authority/decision-maker identification
- Need/pain point recognition
- Timeline signals
- Action Items: Automatically extracted tasks with priorities and due dates
- Key Points: Summary of important discussion topics
- Competitor Mentions: Track competitive intelligence
Supports integration with:
- Salesforce
- HubSpot
- Pipedrive
Each voice note can be automatically synced to create:
- Activity records
- Contact updates
- Opportunity updates
- Task creation
Copy .env.example to .env.local and fill in your credentials:
cp .env.example .env.local-
OpenAI API Key (Get from https://platform.openai.com/api-keys)
NEXT_PUBLIC_OPENAI_API_KEY=sk-proj-your-key-here
-
Clerk Authentication (Get from https://dashboard.clerk.com)
NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY=pk_test_your-key-here CLERK_SECRET_KEY=sk_test_your-key-here
-
Database (Vercel Postgres or any PostgreSQL database)
DATABASE_URL=postgres://user:password@host:5432/database?sslmode=require
The app uses cost-effective GPT-5 Nano for AI analysis:
OPENAI_ANALYSIS_MODEL=gpt-5-nano-2025-08-07
OPENAI_WHISPER_MODEL=whisper-1The app now uses real OpenAI APIs with automatic fallback to mock data if API keys are not configured:
- ✅ Transcription: Integrated with OpenAI Whisper API (
lib/services/transcription.ts) - ✅ AI Analysis: Integrated with GPT-5 Nano (
lib/services/ai-analysis.ts) - 🔄 CRM: Framework ready for OAuth implementation (
lib/services/crm-integration.ts)
-
Fork or Clone the Repository
git clone <repository-url> cd yappnotes
-
Install Dependencies
npm install
-
Set up Clerk Authentication
- Go to https://dashboard.clerk.com
- Create a new application
- Copy your publishable and secret keys
- Add to
.env.local
-
Set up OpenAI API
- Go to https://platform.openai.com/api-keys
- Create a new API key
- Add to
.env.local
-
Deploy to Vercel
npm install -g vercel vercel
-
Set up Vercel Postgres
- In Vercel Dashboard → Storage → Create Database → Postgres
- Copy connection string to environment variables
- Run migrations:
npx prisma db push
-
Add Environment Variables in Vercel
- Go to Project Settings → Environment Variables
- Add all variables from
.env.local
-
Redeploy
vercel --prod
After any schema changes:
# Generate Prisma client
npx prisma generate
# Push schema to database
npx prisma db push
# (Optional) Create migration
npx prisma migrate dev --name your_migration_name- ✅ Voice recording interface
- ✅ OpenAI Whisper transcription integration
- ✅ GPT-5 Nano AI analysis integration
- ✅ Clerk authentication
- ✅ Prisma + Postgres database
- ✅ Dashboard with analytics
- ✅ CRM integration framework
- ✅ Vercel deployment ready
- Database API routes for voice notes
- Save notes to Postgres
- User-specific note filtering
- Real-time note updates
- OAuth flows for CRM platforms
- Meeting summaries and transcripts
- Competitor tracking dashboard
- Team analytics for managers
- Webhooks for CRM sync
- Mobile-responsive improvements
- Mobile app (React Native)
- Opportunity intelligence predictions
- Pipeline forecasting
- Custom analysis rules
- Multi-language support
- Voice note sharing
- Pricing: $49-99 per user/month
- Target ARR: $1M-$10M
- Market: 5-50 person sales teams
- Expansion: Enterprise features, industry-specific models
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License.
For support, email support@fieldintel.com or open an issue in the repository.