Voice Agents for Next.js: what 24 makers' products chose
Among 24 makers' products built with Next.js that we know the voice agents of, LiveKit leads: 15 of them (63%). Next come Daily (5) and Vapi (3).
Hosted platform or open-source framework. Hosted platforms handle phone numbers, turn-taking and provider wiring, and charge per minute on top of model costs. Open-source frameworks give you full control over the pipeline and cost, but you run the real-time servers yourself. A speech-to-speech model skips the chain entirely: one model hears and answers, with less delay but less control over each step.
What makers on Next.js chose
| Option | Next.js products | All makers |
|---|---|---|
| 15 (63%) | 51% | |
| 5 (21%) | 21% | |
| 3 (13%) | 21% | |
| 2 (8%) | 5% | |
| 2 (8%) | 7% |
Live makers' products with a source for both: that they're built with Next.js, and what they use for voice agents. A product using two options counts in both; not market share. "All makers" is the option's share among every maker's product that made this decision.
Which to pick, by situation
- You want a hosted voice agent but need to swap providers and call your own functions
Vapi 3 here - The agent answers or makes business phone calls, set up largely without code
Retell AI 2 here - Voice happens inside your web or mobile app, or you need video too
LiveKit 15 here
Daily 5 here - You want full control over every component of the pipeline, in Python
Pipecat 2 here
LiveKit 15 here
LiveKit
Open-source framework15 Next.js products here (63%).
Best forReal-time voice and video in your own app, with an agents framework on top of its WebRTC infrastructure.
Trade-offMore to learn and run than a hosted platform, unless you pay for LiveKit Cloud.
“LiveKit lets us handle real-time audio/video and screen streaming for research sessions without fighting brittle infra, so we can focus on better participant experiences instead of WebRTC wizardry.”
“LiveKit allowed us to build and scale a virtual meeting platform with a team of two. That's incredible!”
Voice AgentsMaker says so · source ↗“LiveKit handles our real-time communication infrastructure, providing reliable peer-to-peer connections for voice calls across 80+ languages. Their WebRTC implementation ensures crystal-clear audio quality worldwide.”
Voice AgentsMaker says so · source ↗“We use LiveKit as the orchestrator for everything voice-related in our platform — from real-time conversations to AI-driven phone calls. It handles signaling, session management, and audio streaming across our voice AI and telephony systems. The flexibility and performance have been critical to delivering reliable, low-latency voice experiences. Thanks to the LiveKit team for building an infrastructure layer we can trust.”
Voice AgentsMaker says so · source ↗“We are big fans of open source culture. Their UI is good.”
Voice AgentsMaker says so · source ↗“Enables low-latency, high-quality video infrastructure that powers our real-time translation.”
Voice AgentsMaker says so · source ↗“They are the core and inspiration for the whole project.”
Voice AgentsMaker says so · source ↗“LiveKit lets us handle real-time audio/video and screen streaming for research sessions without fighting brittle infra, so we can focus on better participant experiences instead of WebRTC wizardry.”
Voice AgentsMaker says so · source ↗“Amazing infrastructure for using AI voice in your apps.”
Voice AgentsMaker says so · source ↗
Daily
Real-time infrastructure5 Next.js products here (21%).
Best forWebRTC audio and video transport plus Pipecat Cloud, which hosts Pipecat agents so you don't run the real-time servers.
Trade-offHosted only, billed per minute, and you still build the agent logic yourself.
“Pipecat is one of the most popular open-source frameworks for building voice agents, and their TTS integration is clean and well-maintained. A lot of our developers discover us through Pipecat. The community they've built around voice pipelines is hard to beat.”
“Thank you for powering our WebRTC!”
Voice AgentsMaker says so · source ↗“Pipecat is one of the most popular open-source frameworks for building voice agents, and their TTS integration is clean and well-maintained. A lot of our developers discover us through Pipecat. The community they've built around voice pipelines is hard to beat.”
Voice AgentsMaker says so · source ↗“The best WebRTC infrastructure for developers!”
Voice AgentsMaker says so · source ↗“We use Daily's super fast real-time audio infrastructure for streaming audio from clients to our server.”
Voice AgentsMaker says so · source ↗
Vapi
Hosted platform3 Next.js products here (13%).
Best forDevelopers who want to configure every part — models, voices, tools, phone numbers — through an API.
Trade-offPlatform fee per minute plus the pass-through model costs, which makes the total harder to predict.
“Thanks to Vapi for not doing the customizations that I need . Hence today I was not able to build this. You always say that deploy AI agents in minutes rather that months., That statement is very true.”
“Enabling devs to build, test, and deploy advanced voice AI agents. Thanks for being a launch partner!”
Voice AgentsMaker says so · source ↗“Thanks to Vapi for not doing the customizations that I need . Hence today I was not able to build this. You always say that deploy AI agents in minutes rather that months., That statement is very true.”
Voice AgentsMaker says so · source ↗
Retell AI
Hosted platform2 Next.js products here (8%).
Best forPhone agents for bookings and customer service, set up largely through a visual builder.
Trade-offLess room for custom pipelines than building on an open framework.
“We chose Retell because it offers low-latency, interruption-handling voice conversations with reliable telephony integrations, making it far more production-ready for real phone workflows.”
“We chose Retell because it offers low-latency, interruption-handling voice conversations with reliable telephony integrations, making it far more production-ready for real phone workflows.”
Voice AgentsMaker says so · source ↗“Retell powers our AI model and is a fantastic partner to work with”
Voice AgentsMaker says so +1 · source ↗
Pipecat
Open-source framework2 Next.js products here (8%).
Best forA Python pipeline where you choose and swap every speech, LLM and voice component.
Trade-offYou host and scale the real-time processes yourself.
“Open source, vendor neutral, framework for building voice and AI-native experiences”
“Open source, vendor neutral, framework for building voice and AI-native experiences”
Voice AgentsMaker says so · source ↗Also chosen, and not seen yet
Real options for voice agents not seen among these Next.js products yet: ElevenLabs, OpenAI API.
Getting voice agents right
Get a working phone or browser call on a hosted platform first; you'll learn where latency and interruptions hurt before writing infrastructure. Watch total response delay — anything over about a second feels broken in conversation. Move to a framework when per-minute fees or missing control become the real constraint.
- Measuring each component's latency on its own and never the full turn, where speech-to-text, the model and text-to-speech add up to a pause users notice.
- Skipping interruption handling, so the agent keeps talking over a caller who has already started answering.
- Giving a phone agent tools that change bookings or accounts without confirming out loud what it's about to do.
The rest of the Next.js stack
What makers' Next.js products chose for their other decisions, the most common pick for each:
- Hosting: Vercel 1,078 of 1,312
- Transactional Email: Resend 493 of 830
- Database: Supabase 171 of 382
- Payments: Stripe 288 of 359
- LLM API: OpenAI API 222 of 301
- Authentication: Clerk 176 of 211
- Web Analytics: Google Analytics 105 of 197
- Product Analytics: PostHog 123 of 168
Questions
What do most Next.js apps use for voice agents?
Among 24 makers' products built with Next.js that we know the voice agents of, LiveKit leads: 15 of them (63%). Next come Daily (5) and Vapi (3).
How this is counted: a product is on Next.js when a live-product source says so (the maker, its website, a customer story or a subprocessor list), and the same for its voice agents. How evidence is collected.