# The 5 best voice AI APIs and infrastructure (2026) — The Agents Index

> Source: https://theagentsindex.com/category/voice-ai-apis (curated, re-verified)

Speech-to-text, text-to-speech and real-time voice APIs and frameworks that voice agents are built on.

5 agents in this category, ranked by what we can confirm about each (a public price, an API and docs, independent sources, stated limits; payment never changes the order). Each name links to its answer-first markdown twin.

| Name | What it is | Pricing | API |
| --- | --- | --- | --- |
| [LiveKit Agents](https://theagentsindex.com/livekit-agents.md) | Open-source Python and Node.js framework for voice AI agents, with LiveKit Cloud hosting, telephony and observability. | Free, then $50/month | Yes |
| [Cartesia](https://theagentsindex.com/cartesia.md) | Real-time speech models and a managed runtime for production phone and web voice agents. | Free, then $5/month | Yes |
| [Deepgram Voice Agent API](https://theagentsindex.com/deepgram-voice-agent-api.md) | One WebSocket API that runs speech-to-text, LLM orchestration and text-to-speech for real-time voice agents. | From $0.05/minute | Yes |
| [OpenAI Realtime API](https://theagentsindex.com/openai-realtime-api.md) | Speech-to-speech API for voice agents, with tools, MCP and WebRTC or WebSocket transport. | From $10/1m audio input tokens | Yes |
| [sipgate flow](https://theagentsindex.com/sipgate-flow.md) | EU-hosted real-time voice and telephony API that puts your own AI agent on the phone. | On quote | Yes |