The Voice & Video AI Agent Stack, Curated

Compare the agent platforms, speech APIs, avatars, and infrastructure you need to build real-time voice and video agents. Every listing is verified and updated weekly.

All tools

33 tools

Frameworks & Infrastructure

AgentCall

Phone numbers, SMS and AI voice calling built for AI agents

Usage-based, numbers from $2/mo plus per-minute fees

Agent Platforms

Bland AI

Enterprise platform for building and running AI phone agents

Per-minute plans plus enterprise contracts

Speech APIs (STT/TTS)

Cartesia

Ultra-low-latency, expressive voice models for real-time AI

Freemium, paid subscription tiers

Frameworks & Infrastructure

Daily

Real-time video and audio APIs, backers of Pipecat

Usage-based, free tier included

Speech APIs (STT/TTS)

Deepgram

Speech-to-text, text-to-speech and voice agent APIs

Usage-based with free starting credit

Agent Platforms

Dograh

Open-source, self-hostable alternative to Vapi and Retell

Open source free to self-host, paid hosted cloud

Video Agents & Avatars

Eclatira

Conversational voice and video agents that plug into any app

Freemium, paid plans from $19/mo

Speech APIs (STT/TTS)

ElevenLabs

Lifelike text-to-speech, voice cloning and conversational agents

Freemium, paid tiers from about $5/mo

Video Agents & Avatars

HeyGen

AI avatar video creation, translation and interactive avatars

Freemium, paid plans from about $29/mo

Speech APIs (STT/TTS)

Hume AI

Emotionally intelligent voice AI and expressive speech models

Usage-based with free tier

Video Agents & Avatars

LemonSlice

Interactive real-time AI avatars generated from any image

Subscription from $8/mo, custom enterprise pricing

Testing & Voice Apps

Lipi

Local-first dictation that pastes text into any app

Free and open source

Frameworks & Infrastructure

LiveKit

Open-source realtime framework and cloud for voice and video agents

Open source plus usage-based cloud

Testing & Voice Apps

Loqua

AI voice typing and voice-driven workflows for Mac and Windows

Subscription, paid plans from about $9/mo

Testing & Voice Apps

MoshiLin

Practice languages worldwide through live voice chat with AI translation

Not publicly listed

Testing & Voice Apps

Sasu

Open-source voice agent for macOS in English, Tamil and Tanglish

Free and open source

Speech APIs (STT/TTS)

Speechmatics

Enterprise speech recognition and voice AI in many languages

Usage-based with free tier, enterprise plans

Agent Platforms

Synthflow

No-code voice AI agents for sales, support and scheduling

Subscription plans with included minutes

Video Agents & Avatars

Tavus

Real-time conversational video AI with lifelike digital humans

Freemium, paid plans by minutes

Frameworks & Infrastructure

Telnyx

Carrier-grade voice API and infrastructure for AI phone agents

Usage-based per number and minute

Agent Platforms

Vapi

Developer platform for building and deploying voice AI agents

Usage-based, per-minute pricing

Testing & Voice Apps

Voicera

Speak naturally and get polished, AI-edited text anywhere you type

Freemium, paid plans from about $4/mo