AI tools for voice agents

Deepgram is a voice AI platform that exposes speech-to-text, text-to-speech and conversational agents through APIs.

NPCs that actually think

Vocode is an open-source toolkit for building voice-based AI agents.

Sub-second speech-to-text across 55+ languages with AI voice agents

Fixie

Hume EVI, the Empathic Voice Interface, is a voice AI API for building agents that pick up on how a person sounds as well as what they say.

The OpenAI Realtime API is a developer interface for building voice agents that listen and speak in real time.

Pipecat is an open-source Python framework for building voice and multimodal AI agents that talk in real time.

LiveKit Agents is an open source framework and cloud platform for building voice, video and physical AI agents and running them in production.

The Deepgram Voice Agent API is one real-time API that combines speech recognition, language model orchestration and speech synthesis, so developers do not have to stitch separate services together.

Developers building real-time communication features into apps get a complete solution that handles voice, video, chat, and live streaming through APIs and SDKs

ElevenLabs API is a developer interface to the company's audio models.

Builders can add conversational chat or voice agents, give them autonomous capabilities such as planning and escalating work items, and connect them to business data through more than 1,500 pre-bui...

Microsoft Azure AI Speech, now branded Azure Speech in Foundry Tools, is a cloud service for adding voice to applications and agents.

Tiledesk is an open-source, no-code platform for building AI chatbots and agents that automate conversations and connect live agents when a person is needed.

No free plan here

The OpenAI Agents SDK is a Python package for building agentic applications with very few abstractions.