Request a callbackBook a call
ai voice agent development

AI Voice Agent Development: production agents at 2.5¢/minute, not 10¢

An AI voice agent runs about 8 to 15 cents per minute on platforms like Retell, Vapi or Bland. A custom agent built on LiveKit runs closer to 2.5 cents per minute at the same quality. I know because I shipped exactly that in production: a proprietary LiveKit pipeline with optimized STT and TTS that replaced a vendor stack and cut cost about 75 percent, across thousands of AI interview calls. Axionry handles the full AI voice agent development for your use case, whether it's a phone agent, an AI receptionist, outbound calling or an AI interviewer.

Request a callbackBook a 20-min call ↗
Ask AI about this pageAsk ClaudeAsk ChatGPTAsk Perplexity
Proof point
2.5¢/min in production
A headset resting on a desk at night, lit by a single band of light, the hardware behind a production voice agent
How you pay

Get it built at $0.

That is not a discount. It is when you pay. The work is split into checkpoints with acceptance criteria written down before anything starts, and each checkpoint is invoiced only after you have seen it and accepted it. No deposit.

$0 to start
You hold every dollar until a checkpoint is delivered and you accept it. No approval, no invoice.
Fixed cost, unlimited features
Or hire the team outright: one fixed monthly cost, unlimited feature development, any stack.
The engineer takes your call
The person on your first call is the one who architects and writes it. No account managers, no bench time.

A US agency quotes $50,000 to $150,000 for the same build and asks for 40 to 50% of it before a line is written. Account managers, project managers, sales commission and bench time. None of it appears in your product.

Start at $0Book a 20-min call ↗
Architecture diagram of a production voice agent at 2.5 cents a minute: a caller reaches a SIP phone line connected to a LiveKit agent that runs speech to text, an LLM and text to speech in sequence and returns a spoken reply. The LLM calls tools for the calendar, the CRM and transfer to a person, and every call produces recordings, transcripts and QA scores. Production cost fell from 10 cents to 2.5 cents a minute.
The stack behind our 2.5¢ a minute production number, down from 10¢ on a vendor platform.

What can a custom voice AI agent do?

It can answer and qualify inbound calls 24/7 as an AI receptionist or answering service, run outbound campaigns with natural conversation, and conduct structured AI interviews at scale (the system I built powers assessments for 20+ enterprise clients). It books appointments, takes orders and routes to humans with full context, and it speaks with sub-second latency using a streaming STT, LLM and TTS pipeline.

Why custom instead of Retell, Vapi or Bland?

Platforms are the right choice for a weekend prototype. At scale, their 8 to 15 cents a minute becomes your margin. At 100K minutes a month, the gap between 10¢ and 2.5¢ is about $90,000 a year. You also own the stack: your own turn-taking logic, your own model routing, no per-seat lock-in, and the freedom to swap STT or TTS providers the day a cheaper one ships.

I integrated Retell in 48 hours for AccioJob (their published case study, a 70% false-positive reduction), then engineered our own LiveKit stack that took the marginal cost near zero on committed infrastructure. I've lived both sides, and I'll tell you plainly which one your stage actually needs.

Stack and delivery

The stack is LiveKit for WebRTC transport and the agents framework, xAI for streaming STT and TTS, Gemini 2.5 Flash-Lite for LLM routing, and telephony over Telnyx SIP. Self-hosted agent workers keep the marginal cost near zero on committed infrastructure. Everything ships with full observability: transcripts, latency traces and cost per call. It's delivered as your infrastructure, on your accounts, as your IP.

Pricing

EngagementScopePrice
Voice Agent MVPOne production use case, telephony + dashboard (3 to 4 weeks)from $12,000
Platform MigrationRetell/Vapi/Bland → your own LiveKit stackfrom $8,000
Cost AuditPer-minute cost breakdown + reduction roadmap$1,500 fixed
Free toolPrice your build with the AI product cost estimatorPick the features, the stack, agents and voice. See the cost, the timeline and what it costs to run.
Further reading

What should you read before you build it?

Products we build

What you can build with this, at $0

All products →
AI receptionist: the Callwren portal, an example of the finished productAI receptionistAnswers every call, books appointments into your calendar and hands urgent callers to your team.Build at $0From $19,000 · 5 to 9 weeksAI voice agent: the Voxlane portal, an example of the finished productAI voice agentA voice agent for inbound and outbound calls, with its knowledge, tools and call logs on your own stack.Build at $0From $25,500 · 7 to 11 weeksAI call center: the Linebright portal, an example of the finished productAI call centerAnswers thousands of calls a day from your knowledge base and passes the rest to your team with a summary.Build at $0From $38,500 · 9 to 16 weeksAI sales agent: the Leadquill portal, an example of the finished productAI sales agentCalls every inbound lead within a minute, qualifies it, books the demo and writes the result to your CRM.Build at $0From $22,000 · 6 to 10 weeksAI payment reminder agent: the Duebell portal, an example of the finished productAI payment reminder agentCalls customers before payments fall due, sends a pay link by SMS or WhatsApp and confirms each payment.Build at $0From $22,500 · 6 to 11 weeksAI debt collection agent: the Arrearo portal, an example of the finished productAI debt collection agentCalls overdue borrowers within the rules, checks identity, logs promises to pay and routes disputes to people.Build at $0From $32,500 · 8 to 14 weeks
FAQ

Common questions.

Straight answers. If yours isn't here, ask on a 20-minute call.

How much does an AI voice agent cost per minute?+

Managed platforms charge roughly 8 to 15 cents per minute all-in. A custom stack on LiveKit with optimized STT/TTS runs at about 2.5¢ per minute in production, a 75% reduction I achieved in a live system handling AI interviews at scale.

Retell vs Vapi vs a custom LiveKit stack: which should I choose?+

Use Retell or Vapi to validate an idea in days. Move to a custom LiveKit stack when volume passes ~20K minutes a month, where owning the pipeline pays for itself within a quarter. I've shipped production systems on both and can migrate you without downtime.

How long does AI voice agent development take?+

3 to 4 weeks for a single production use case including telephony, interruption handling and monitoring. I once integrated a full vendor voice stack in 48 hours; custom builds take longer because you own everything at the end.

Can voice agents really replace human callers?+

For structured conversations like screening, booking, qualification and interviews, yes, and measurably: our AI interview system cut false-positive assessments by 70% (published Retell AI case study). For nuanced sales negotiation, agents assist rather than replace.

Ready to talk numbers?

Twenty minutes, straight to the engineer. No sales rep, no deck.

Request a callbackBook a call ↗