Python Voice Tracking — Manual Integration

Implement complete voice billing flows in Python using Paygent’s Session-based tracking.

Voice Pricing

As an architect with decades of experience in high-throughput billing systems, I can tell you that flexibility is the heartbeat of a successful AI platform.

Scenario A: Per-minute ON

Real-World Scenario: You run a dental clinic AI that handles appointment bookings. You want to charge based on the actual conversation time because longer calls use more compute resources.

When you enable the Per-minute toggle on your Indicator, Paygent calculates the total duration reported in your set_voice_indicator call.

Pricing: $0.15 / min
Duration: 5.0 mins
Result: 5 * 0.15 = $0.75

Result: Perfect for connectivity-based SaaS where you pass on infrastructure costs with a margin.

Configuring the Activity Indicator with the Per-minute toggle ON.

Scenario B: Per-minute OFF

Real-World Scenario: You’ve built a world-class Lead Qualification agent. Your customers don’t care how long the call lasts; they only care that the lead was qualified successfully.

Disable the Per-minute toggle. Now, no matter if the call lasts 1 minute or 20 minutes, the customer is charged a single fixed rate.

Pricing: $0.20 / call
Duration: Any
Result: Flat $0.20

Result: Ideal for outcome-based services where your value is tied to task completion, not duration.

Configuring the Activity Indicator with the Per-minute toggle OFF.

Custom Pricing

In modern AI architectures, one size rarely fits all. You might use GPT-5 for high-stakes negotiation agents, but switch to Gemini 2.5 for simple data entry tasks.

Real-World Custom Example:

Paygent automatically detects the models you track via track_voice_stt, track_voice_llm, and track_voice_tts. You can then set unique per-minute rates for each tier:

• LLM: GPT-5 (Premium): $0.50 / min
• LLM: Gemini 2.5 (Standard): $0.20 / min
• STT: Deepgram Nova-2: $0.05 / min
• TTS: Azure Neural: $0.08 / min

“With Custom Pricing, you no longer subsidize expensive models with cheap ones. Your margins stay protected while you provide the best possible AI experience.”

Complete Voice Session Flow

This example shows how to manage a voice session from start to finish:

1
import time
2
from paygent_sdk import Client
3
from paygent_sdk.models import CustomerCreateOrGetRequest
4
from paygent_sdk.constants import ServiceProvider, DeepgramSTTModels, AmazonPollyTTSModels
5
6
client = Client(api_key="your-paygent-api-key")
7
8
customer_id = "customer-123"
9
agent_id = "voice-agent-id"
10
11
# 1. Create or Get Customer (Automated)
12
client.create_or_get_customer(CustomerCreateOrGetRequest(
13
    name="Customer Name",
14
    external_id=customer_id
15
))
16
17
# 2. Define a unique session ID
18
# Use your own unique session ID for this customer (e.g., call SID or UUID)
19
session_id = f"voice_call_{int(time.time() * 1000)}"
20
21
# 3. Initialize Voice Session
22
client.initialize_voice_session(session_id, agent_id, customer_id)
23
24
# 4. Track User Speech (STT Usage)
25
client.track_voice_stt(session_id, {
26
    'serviceProvider': ServiceProvider.DEEPGRAM,
27
    'model': DeepgramSTTModels.NOVA_2,
28
    'plan': 'default',
29
    'audioDuration': 20 # audio duration in minutes
30
})
31
32
# 5. Track AI Processing (LLM Usage)
33
client.track_voice_llm(session_id, {
34
    'serviceProvider': ServiceProvider.OPENAI,
35
    'model': 'gpt-4o',
36
    'plan': 'default',
37
    'promptTokens': 1000,
38
    'completionTokens': 500
39
})
40
41
# 6. Track AI Speech (TTS Usage)
42
client.track_voice_tts(session_id, {
43
    'serviceProvider': ServiceProvider.AMAZON_POLLY,
44
    'model': AmazonPollyTTSModels.NEURAL,
45
    'plan': 'default',
46
    'character_count': 28000
47
})
48
49
# 7. Final Step: Set Indicator with Call Duration (Minutes)
50
client.set_voice_indicator(session_id, "voice_call_completed", 0.5)

How it Works

Step 1 — On-the-fly Onboarding

The create_or_get_customer method allows for frictionless user onboarding. If a customer with the external_id doesn’t exist, Paygent creates one automatically.

Step 2 — Session Context

initialize_voice_session sets up a billing context for the call. This ensures all subsequent STT, LLM, and TTS usage is grouped under this single call session.

Step 3 — Detailed Analytics

Track every event within the voice pipeline. Paygent provides deep insights into which models are being used and the associated costs in real-time.

Step 4 — Final Outcome

Finalize the session with set_voice_indicator. Use the duration or outcome-based indicators to accurately bill your customers.