AI Audio Assistant

## 🎙️ VoiceFlow AI: Telegram + Deepgram + OpenAI + Supabase Audio Assistant

**Who is this for?**
Businesses, customer service teams, content creators, and organizations who want to provide intelligent voice-based interactions through Telegram. Perfect for accessibility-focused services, multilingual support, or hands-free customer assistance.

**What problem does this solve?**
- Enables natural voice conversations with AI
- Breaks down language and accessibility barriers  
- Provides instant voice responses to customer queries
- Reduces typing requirements for users
- Offers 24/7 voice-based customer support
- Maintains conversation context across voice interactions
- Handles both voice and text messages seamlessly

**What this workflow does:**
1. Receives voice OR text messages via Telegram bot
2. For voice: Transcribes audio using Deepgram's speech-to-text API
3. Processes queries through AI agent with knowledge base access
4. Generates intelligent responses based on conversation context
5. For voice input: Converts AI response to natural speech using Deepgram TTS
6. Sends appropriate response (audio for voice, text for text) back to user
7. Maintains conversation memory for contextual interactions

**Setup Instructions:**
1. Get Telegram bot token from @BotFather
2. Sign up for Deepgram API (STT + TTS services)
3. Configure OpenAI API key for AI responses
4. Set up Supabase knowledge base table
5. Update API credentials in workflow nodes
6. Test with both voice and text messages

**Key Features:**
- Dual input support (voice and text)
- Intelligent response routing
- Voice-to-voice conversation capability
- Knowledge base integration
- Conversation memory
- Professional AI responses