💬 🎙️ VoiceFlow AI: Telegram + Deepgram + OpenAI + Supabase audio assistant

⚡ 2,167 views · 💬 Support Chatbots

Description

🎙️ AI Audio Assistant with Voice-to-Voice Response

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?

What this workflow does:

  1. Receives voice messages via Telegram bot
  2. Transcribes audio using Deepgram’s advanced speech-to-text
  3. Processes transcribed text through AI agent with knowledge base access
  4. Generates intelligent responses based on conversation context
  5. Converts AI response to natural-sounding speech using Deepgram TTS
  6. Sends audio response back to user via Telegram
  7. Maintains conversation memory for contextual interactions

🔧 Technical Architecture

Core Components:

Data Flow:

  1. Voice Message → Telegram API → File Download
  2. Audio File → Deepgram STT → Transcript
  3. Transcript → AI Agent → Response Generation
  4. Response → Deepgram TTS → Audio File
  5. Audio Response → Telegram → User

🛠️ Setup Instructions

Prerequisites

  1. Telegram Bot Token

    • Create bot via @BotFather
    • Get bot token and configure webhook

  2. Deepgram API Key

    • Sign up at deepgram.com
    • Get API key for STT and TTS services
    • Note: Currently hardcoded in workflow

  3. OpenAI API Key

    • OpenAI account with API access
    • Configure in OpenAI Chat Model node

  4. Supabase Database

    • Create Supabase project
    • Set up knowledge_base table
    • Configure API credentials

Step-by-Step Setup

  1. Configure Telegram Bot

    - Update telegramToken in "Prepare Voice Message Data" node
- Set correct bot token in Telegram nodes
- Test bot connectivity

  2. Set Up Deepgram Integration

    - Replace API key in "Transcribe with Deepgram" node
- Update TTS endpoint in "HTTP Request" node
- Test voice transcription accuracy

  3. Configure Knowledge Base

    -- Create knowledge_base table in Supabase
CREATE TABLE knowledge_base (
  id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
  question TEXT NOT NULL,
  answer TEXT NOT NULL,
  category VARCHAR(100),
  keywords TEXT[],
  created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW()
);

  4. Customize AI Prompts

    • Update system message in “Telegram AI Agent” node
    • Adjust temperature and max tokens in OpenAI model
    • Configure memory session keys

  5. Test End-to-End Flow

    • Send test voice message to bot
    • Verify transcription accuracy
    • Check AI response quality
    • Validate audio output clarity

🎛️ Configuration Options

Voice Recognition Settings

AI Response Settings

Text-to-Speech Settings

🔒 Security Considerations

API Key Management

// Current implementation has hardcoded tokens
// Recommended: Use environment variables
const telegramToken = process.env.TELEGRAM_BOT_TOKEN;
const deepgramKey = process.env.DEEPGRAM_API_KEY;

Data Privacy

📊 Monitoring & Analytics

Key Metrics to Track

// Add to workflow for monitoring
console.log({
  timestamp: new Date().toISOString(),
  user_id: userData.user_id,
  transcript_confidence: transcriptData.confidence,
  response_length: aiResponse.length,
  processing_time: processingTime
});

🚀 Customization Ideas

Enhanced Features

  1. Multi-language Support

    • Add language detection
    • Support multiple TTS voices
    • Translate responses

  2. Voice Commands

    • Implement wake words
    • Add voice shortcuts
    • Create voice menus

  3. Advanced AI Features

    • Sentiment analysis
    • Intent classification
    • Escalation triggers

  4. Integration Expansions

    • Connect to CRM systems
    • Add calendar scheduling
    • Integrate with help desk tools

Performance Optimizations

🐛 Troubleshooting

Common Issues

Voice Not Transcribing

Poor Audio Quality

AI Responses Too Generic

Memory Not Working

💡 Best Practices

Voice Interface Design

Knowledge Base Management

User Experience

📈 Success Metrics

Technical KPIs

Business KPIs

🔄 Maintenance Schedule

Daily

Weekly

Monthly

📚 Additional Resources

Community Support

Note: This template requires active API subscriptions for Deepgram and OpenAI services. Costs may apply based on usage volume.

🔗 Nodes Used

HTTP Request, Telegram, Telegram Trigger, AI Agent, OpenAI Chat Model, Simple Memory

📥 Import

Download workflow.json and import into n8n: Workflow menu → Import from File

📖 Importing guide · 🔑 Credential setup