Skip to main content

Integrations

Welcome to the Votel Integrations documentation. This section covers the core integrations that power your AI voice agents.

What's Available

Votel integrates with industry-leading AI providers to deliver intelligent, lifelike voice experiences:

Large Language Models (LLMs) The "brain" of your voice agent. LLMs handle understanding, reasoning, and generating intelligent responses in natural language. Votel supports multiple OpenAI models, from fast and efficient GPT-4o Mini to the advanced reasoning capabilities of GPT-4 Turbo.

Text-to-Speech (TTS) Voices The "voice" of your agent. TTS systems convert text responses into natural, human-like speech. Votel integrates with premium providers like ElevenLabs, OpenAI Voices, and Cartesia to deliver expressive, emotionally intelligent audio output.

How They Work Together

  1. Speech-to-Text: User input is transcribed into text
  2. LLM Processing: The language model understands and generates a response
  3. Text-to-Speech: The response is converted to natural voice
  4. Voice Output: The agent speaks to the user

This seamless integration between intelligence (LLM) and personality (TTS) creates voice agents that are both smart and engaging.


Explore the sections below to learn more about each integration type and how to configure them for your use case.