Skip to main content

​
Supported Providers

​
Language Models (LLMs)

CallIntel integrates with multiple LLM providers:

OpenAI

GPT-4, GPT-3.5 Turbo, and other models

Google Gemini

Gemini Pro and vision-enabled models

Qwen (Alibaba)

Qwen models for cost-effective inference

Claude

Anthropic’s Claude models (coming soon)

​
Voice Input (Speech-to-Text)

AssemblyAI

Real-time speech recognition

Deepgram

Low-latency speech-to-text

Cartesia

Enterprise speech recognition

​
Voice Output (Text-to-Speech)

OpenAI

Natural voice synthesis

Cartesia

High-quality voice output

ElevenLabs

Realistic voice cloning

Rime AI

Fast, natural synthesis

Inworld AI

Interactive character voices

​
Speaker Identification (Diarization)

Pyannote

Identify and distinguish speakers

​
Model Selection Guide

​
Choosing a Language Model

For General Purpose:
  • OpenAI GPT-4 - Best quality, highest cost
  • OpenAI GPT-3.5 Turbo - Great quality, more affordable
  • Gemini Pro - Good quality, competitive pricing
For Cost-Effective:
  • Qwen Models - Lower cost, reasonable quality
  • GPT-3.5 Turbo - Balance of quality and cost
For Specific Tasks:
  • Customer Service - GPT-3.5 Turbo recommended
  • Technical Support - GPT-4 recommended
  • Sales Calls - Gemini Pro recommended
  • High Volume - Qwen recommended

​
Choosing a Speech-to-Text Provider

For Real-Time Performance:
  • Deepgram - Lowest latency (200ms)
  • Cartesia - Enterprise-grade performance
  • AssemblyAI - Reliable and scalable
For Accuracy:
  • Deepgram Nova 2 - Best accuracy
  • Cartesia - Domain-specific models
  • AssemblyAI - Excellent general accuracy
For Cost:
  • AssemblyAI - Competitive pricing
  • Deepgram - Flexible pricing tiers
  • Cartesia - Enterprise custom pricing

​
Choosing a Text-to-Speech Provider

For Natural Sound:
  • OpenAI - Most natural, good variety
  • ElevenLabs - Premium quality voices
  • Cartesia - Studio-quality audio
For Speed:
  • Rime AI - Fastest synthesis
  • Cartesia - Enterprise performance
  • OpenAI - Good balance
For Voice Variety:
  • ElevenLabs - Extensive voice library
  • OpenAI - Multiple voices, multiple languages
  • Inworld AI - Character-specific voices

​
Configuration

​
Setting Up Your API Keys

Each provider requires API credentials: Step 1: Obtain API Key
  • Visit provider’s dashboard
  • Create API key in settings
  • Copy key securely
Step 2: Add to CallIntel
  1. Go to Developer Settings
  2. Select “API Keys” section
  3. Paste provider API key
  4. Save configuration
Step 3: Test Connection
  • Click “Test” button
  • Verify successful connection
  • Save settings

​
Organization-Level Setup

Super Admins configure providers globally: 
1. Admin Dashboard → Settings
2. Select provider (OpenAI, Gemini, etc.)
3. Enter API key
4. Configure rate limits
5. Enable/disable provider
6. Save

​
Agent-Level Configuration

Organizations select providers per agent: 
1. Create/Edit Agent
2. Select Language Model (LLM)
3. Select Speech-to-Text (STT)
4. Select Text-to-Speech (TTS)
5. Save agent

​
Quick Start

​
Basic Setup (5 minutes)

1

Choose OpenAI

Start with OpenAI GPT-3.5 for best results
2

Get API Key

Visit https://platform.openai.com/api-keys
3

Add to CallIntel

Settings → API Keys → Add OpenAI
4

Create Agent

Use OpenAI model in new agent
5

Make Test Call

Test agent with web call

​
Cost Optimization

​
Token Usage Tips

Reduce Token Consumption:
  • Shorter knowledge bases (only essential info)
  • Concise system prompts
  • Lower max_tokens setting
  • Filter conversations to relevant context
Example Cost Reduction: 
Before:
- Long KB: 5,000 tokens per call
- Verbose prompt: 2,000 tokens
- Total: 7,000 tokens × $0.002 = $0.014 per call

After:
- Optimized KB: 2,000 tokens
- Concise prompt: 500 tokens
- Total: 2,500 tokens × $0.002 = $0.005 per call

Savings: 65% reduction

​
Batch Processing

Use batch endpoints for non-real-time calls:
  • Batch pricing: 50% discount
  • Perfect for scheduled campaigns
  • Save costs on high-volume calls

​
Model Selection Strategy

High Volume + Cost Sensitive:
→ Use Qwen models (lowest cost)

Quality Critical:
→ Use GPT-4 or Claude (best quality)

Balanced Approach:
→ Use GPT-3.5 Turbo (sweet spot)

Real-Time Performance:
→ Pair with Deepgram STT

​
Detailed Provider Guides

OpenAI Models

Complete guide to GPT-4, GPT-3.5, and more

Google Gemini

Integrate Google’s Gemini models

Speech Recognition

AssemblyAI, Deepgram, Cartesia setup

Voice Synthesis

OpenAI, ElevenLabs, Cartesia voices

Speaker Diarization

Identify and distinguish speakers

Overview

Compare all AI providers

​
Troubleshooting

Edit your agent configuration, select a different model from the dropdown, and save. Existing calls continue with old model; new calls use new model.
Check your STT provider latency, LLM response time, and TTS speed. Try switching to faster providers like Deepgram and Rime AI.
Verify API key is correct, not expired, and has proper permissions. Regenerate key if necessary.
Check your provider’s dashboard (OpenAI, Gemini, etc.) for real-time usage metrics and costs.

​
Support

API Documentation

View complete provider documentation

Integration Help

Email: callintel01@gmail.com