DEV Community

Sonam
Sonam

Posted on

Route Voicemails with Python and Telnyx AI

#python #ai #flask #automation

I built a small Flask example that turns voicemail into a routing workflow.

Code:

https://github.com/team-telnyx/telnyx-code-examples/tree/main/voicemail-smart-router-python

The app accepts either:

  • a voicemail transcript
  • an uploaded voicemail audio file

For audio, it transcribes the voicemail first. Then it uses Telnyx AI Inference to classify the message and decide where it should go.

Categories

The app classifies voicemails into:

  • urgent
  • billing
  • support
  • sales
  • spam
  • routine

Each category maps to a route:

urgent  -> Slack alert
billing -> email
support -> ticket queue
sales   -> CRM lead
spam    -> blocklist + archive
routine -> daily digest
Enter fullscreen mode Exit fullscreen mode

Run it 

git clone https://github.com/team-telnyx/telnyx-code-examples.git
cd telnyx-code-examples/voicemail-smart-router-python
cp .env.example .env
pip install -r requirements.txt
python app.py
Enter fullscreen mode Exit fullscreen mode

Configure .env:

TELNYX_API_KEY=your_telnyx_api_key
AI_MODEL=zai-org/GLM-5.2
FALLBACK_MODEL=meta-llama/Llama-3.3-70B-Instruct
HOST=127.0.0.1
Enter fullscreen mode Exit fullscreen mode

Optional Slack webhook for urgent messages:

SLACK_WEBHOOK=https://hooks.slack.com/...
Enter fullscreen mode Exit fullscreen mode

Classify a transcript 

curl -X POST http://localhost:5000/voicemails/transcript \
  -H "Content-Type: application/json" \
  -d '{
    "transcript": "This is an emergency. Our production system is down and we need help immediately.",
    "caller_number": "+17177247292"
  }'
Enter fullscreen mode Exit fullscreen mode

Example response:

{
  "category": "urgent",
  "confidence": 1.0,
  "priority": "high",
  "reason": "The caller reports a production system outage requiring immediate attention.",
  "suggested_action": "Escalate immediately to the on-call engineering team.",
  "route": "slack",
  "routed_to": "#oncall-alerts",
  "routing_status": "delivered"
}
Enter fullscreen mode Exit fullscreen mode

Process voicemail audio 

curl -X POST http://localhost:5000/voicemails/process \
  -F "file=@voicemail.wav" \
  -F "caller_number=+17177247292"
Enter fullscreen mode Exit fullscreen mode

For audio, the app calls:

POST /v2/ai/audio/transcriptions
Enter fullscreen mode Exit fullscreen mode

using:

distil-whisper/distil-large-v2
Enter fullscreen mode Exit fullscreen mode

Then it calls:

POST /v2/ai/chat/completions
Enter fullscreen mode Exit fullscreen mode

to classify the transcript.

Routes included

  • POST /voicemails/transcript
  • POST /voicemails/process
  • GET /voicemails
  • GET /voicemails/<id>
  • GET /routes
  • GET /health

Production ideas

This sample uses in-memory storage and a simple routing map.

For production, I would add:

  • auth
  • durable storage
  • webhook ingestion from real voicemail events
  • retries for failed delivery
  • real email, ticket, and CRM integrations
  • review queues for low-confidence messages
  • audit logs
  • configurable routing rules
  • PII handling before storing transcripts

The useful pattern is not just classification. It is classification plus action. The model turns a voicemail into structured intent, and the application routes it to the right workflow.

Resources:

Top comments (0)