Talkform
deepseek-v4-flashrun 4 Sep 2026930,169 tokens
Instructions
Instructions — the case's current instructions
build a typeform competitor where the backend is identical to typeform with structured questions and answers, but the frontend is purely an AI voice interview, with the AI interviewer aware of what structured data it needs to fill in for the user, but asking in a more natural conversational way. get it running including auth just ask me for the API keys for the services you need.
build a typeform competitor where the backend is identical to typeform with structured questions and answers, but the frontend is purely an AI voice interview, with the AI interviewer aware of what structured data it needs to fill in for the user, but asking in a more natural conversational way. get it running including auth just ask me for the API keys for the services you need.
TalkForm — AI Voice Interview Platform
A Typeform competitor where forms are built with structured questions but collected via an AI voice interview. The AI interviewer understands the schema and conducts a natural, conversational interview.
Architecture
┌─────────────────┐ ┌─────────────────┐
│ Frontend │ │ Backend │
│ React + Vite │────▶│ Express + │
│ Port 5173 │ │ SQLite │
│ │ │ Port 3001 │
└─────────────────┘ └─────────────────┘
│
┌───────┴───────┐
│ OpenAI API │
│ (AI Voice) │
└───────────────┘
Project Structure
workspace/
├── backend/
│ ├── src/
│ │ ├── db.js # SQLite database setup
│ │ ├── index.js # Express server entry
│ │ └── routes/
│ │ ├── auth.js # Registration, login, JWT
│ │ ├── forms.js # CRUD for forms & questions
│ │ ├── responses.js # Response collection
│ │ └── interview.js # AI interview chat & extraction
│ ├── .env # Config (PORT, JWT_SECRET, OPENAI_API_KEY)
│ └── package.json
├── frontend/
│ ├── src/
│ │ ├── App.jsx # Router setup
│ │ ├── index.css # All styles
│ │ ├── main.jsx # React entry
│ │ └── pages/
│ │ ├── Login.jsx # Auth sign-in
│ │ ├── Register.jsx # Auth register
│ │ ├── Dashboard.jsx # List & create forms
│ │ ├── FormBuilder.jsx# Build structured forms
│ │ ├── Interview.jsx # AI voice interview UI
│ │ └── Responses.jsx # View collected responses
│ ├── index.html
│ ├── vite.config.js
│ └── package.json
└── README.md
Setup & Running
1. Set your OpenAI API key
Edit backend/.env:
OPENAI_API_KEY=sk-your-real-key-here
2. Start the backend
cd backend
npm start
Backend runs on http://localhost:3001. Creates talkform.db automatically on first run.
3. Start the frontend
In a separate terminal:
cd frontend
npm run dev
Frontend runs on http://localhost:5173.
4. Open the app
- Register → create an account
- Dashboard → click "+ New Form" to create a form
- Form Builder → add structured questions (short text, rating, multiple choice, yes/no, etc.)
- Interview Mode → click the "Interview Mode" button (or share the link) to start an AI voice interview
- Inside the interview, type or use the microphone button 🎤 to speak your answers
- After the interview, answers are extracted and saved to the structured form
Database
SQLite file at backend/talkform.db. Schema:
users— accountsforms— form metadataquestions— structured questions (type, label, required, options)responses— interview sessionsanswers— extracted answers linked to questions
API Endpoints
| Method | Path | Description |
|---|---|---|
| POST | /api/auth/register |
Create account |
| POST | /api/auth/login |
Sign in |
| GET | /api/forms |
List user's forms |
| POST | /api/forms |
Create form |
| GET | /api/forms/:id |
Get form + questions |
| PUT | /api/forms/:id |
Update form |
| DELETE | /api/forms/:id |
Delete form |
| PUT | /api/forms/:id/questions |
Batch save questions |
| GET | /api/forms/public/:id |
Public form access |
| POST | /api/responses/form/:id/start |
Start interview response |
| POST | /api/responses/:id/answer |
Submit single answer |
| POST | /api/responses/:id/complete |
Mark interview complete |
| GET | /api/responses/:id |
Get response + answers |
| GET | /api/responses/form/:id |
All responses for form |
| POST | /api/interview/chat |
AI interview chat |
| POST | /api/interview/extract |
Extract answers from conversation |
How the AI Interview Works
- The form's structured questions (with types, labels, options) are sent to OpenAI as a JSON schema
- The AI receives a system prompt instructing it to act as a natural voice interviewer
- The conversation history is sent with each request so the AI maintains context
- When the interview concludes, a separate extraction call parses the conversation and saves structured answers
- The frontend supports both text input and browser speech recognition (Web Speech API)