Skip to content
LLM Pricing Calc
LLM pricing last verified Voice provider rates

AI Voice Agent Cost Calculator: Cost per Minute & per Call

Estimate what an AI phone or voice agent costs per minute, per call and per month across the full STT, LLM, TTS and telephony stack, with or without a Vapi or Retell platform fee.

Twilio US ≈ $0.014 · Telnyx ≈ $0.007 · Web 0

Vapi ≈ $0.05 · Retell ≈ $0.07 · DIY 0

Advanced conversation settings
Prompt caching

Cost per minute

$0.0381

Cost per call

$0.1524

Monthly total

$2,318

Where the money goes

ComponentPer minutePer callMonthlyShare
Speech-to-text$0.0077$0.0308$468.4720%
LLM$0.0023$0.00918$139.636%
Text-to-speech$0.0141$0.0564$858.3037%
Telephony + platform$0.014$0.056$851.7637%

LLM: 16 turns per call, 42,000 input tokens re-read across the call.

Pay-as-you-go list rates for real-time (streaming) usage. Volume discounts and enterprise plans are lower. TTS is billed per character; we convert using ~150 spoken words per minute (~825 characters per minute of agent speech).

Official pricing: Deepgram ↗ · OpenAI ↗ · AssemblyAI ↗ · ElevenLabs ↗ · Cartesia ↗ · Twilio ↗ · Telnyx ↗ · Vapi ↗ · Retell ↗

LLM: Official pricing ↗

Guide

What an AI voice agent costs per minute

An AI phone agent is a pipeline of four metered services running in a loop: speech-to-text (STT) transcribes the caller, an LLM decides what to say, text-to-speech (TTS) speaks the reply, and a telephony carrier connects the call. Each is billed differently (per audio minute, per token, per character and per call minute), which is why voice AI pricing is hard to compare at a glance. The calculator converts everything to a cost per minute. With the defaults above (500 calls a day, 4 minutes each), the stack costs about $0.0381 per minute, or $2,318 a month.

Speech-to-text (STT)

STT is billed per minute of audio, and the full call is transcribed whether or not the caller is speaking. Rates in this calculator range from $0.001 to $0.0077 per minute. Streaming matters more than price: batch transcription is cheaper, but a live agent needs partial transcripts within a few hundred milliseconds to feel responsive.

LLM

The LLM is usually the smallest line item because spoken replies are short, but it behaves like any multi-turn agent: every turn re-sends the system prompt and the conversation so far. At 4 turns a minute, a 4-minute call makes 16 LLM calls and re-reads 42,000 input tokens. Prompt caching keeps that cheap. Long calls with large system prompts and no caching are where LLM cost climbs. The LLM pricing calculator models the same context growth for text agents, and the LLM price table lists the per-token rates behind the LLM dropdown.

Text-to-speech (TTS)

TTS is billed per character generated, only for the share of the call the agent is talking. At about 825 characters per spoken minute and the agent talking 45% of the time, a call minute needs ~371 characters. That puts TTS between $0.00556 and $0.0371 per call minute depending on the voice, and premium voices are often the single largest cost in the stack.

Telephony and platform fees

Carriers such as Twilio and Telnyx charge $0.007–$0.014 per minute for US voice, and a WebRTC agent in a browser or app skips this entirely. Managed platforms such as Vapi and Retell add an orchestration fee of $0.05–$0.07 per minute on top of the underlying providers. That fee buys turn-taking, interruption handling, call transfer and analytics, which take real engineering effort to build. Use the platform field to compare a managed stack with a self-built one.

How to optimize voice agent latency and spend

Voice is the one LLM use case where latency matters as much as price. Callers expect a reply within about 800 ms of finishing a sentence, and the budget is shared across STT finalization, the LLM's time to first token and TTS time to first audio. The cheapest choices are often also the fastest:

  • Pick a fast mid-tier or budget LLM. Flagship and reasoning models add seconds of thinking and cost several times more per token, with little benefit for scripted calls.
  • Stream everything. Streaming STT, token streaming from the LLM and streaming TTS overlap the stages instead of running them back to back.
  • Keep the system prompt short and cached. Fewer input tokens per turn means a faster first token and a lower LLM bill.
  • Match the voice to the call. Use premium TTS voices for sales and brand-sensitive calls and cheaper voices for reminders, surveys and routine support.
  • End calls cleanly. Detect voicemail and silence early, and hang up when the task is done; every idle minute still pays STT and telephony.
  • Negotiate at volume. Past roughly 100K minutes a month, STT, TTS and platform providers all offer committed-use discounts.

At very high volume, self-hosting the LLM or a Whisper model on a dedicated GPU can be cheaper than per-token or per-minute pricing. The API vs self-hosting break-even calculator shows where that crossover sits, and the LLM VRAM calculator tells you which GPU you'd need.

More AI cost tools

Voice agent cost FAQ

How much does an AI voice agent cost per minute?

A self-built stack (streaming STT + a fast mid-tier LLM + a low-latency TTS + Twilio) typically costs $0.03–$0.10 per minute. Managed platforms like Vapi or Retell add a $0.05–$0.07/min platform fee on top, so all-in costs of $0.10–$0.20 per minute are common.

Which part of a voice agent costs the most?

Usually text-to-speech. Premium voices such as ElevenLabs can be 40–60% of the bill. The LLM is often cheaper than people expect, because voice replies are short. Its cost does grow with call length, since every turn re-sends the whole conversation.

How is LLM cost calculated for a voice call?

We estimate turns = turns per minute × call length. Each turn sends the system prompt plus the conversation so far, and generates a short reply. With prompt caching on, everything except the newest exchange is billed at the cached rate.

How are TTS characters estimated?

People speak about 150 words per minute, roughly 825 characters. We multiply that by the share of the call the agent is talking (45% by default) and the call length, then apply the provider's per-1,000-character rate.

How much does an AI phone agent cost per month?

Multiply cost per minute by monthly call minutes. With the defaults on this page (500 calls a day, 4 minutes each, no platform fee) an AI call agent costs about $0.0381 per minute, $0.1524 per call and $2,318 per month. Adding a Vapi or Retell platform fee of $0.05–$0.07 per minute raises that substantially at high volume.

Is Vapi or Retell cheaper than building my own voice stack?

Per minute, no: managed platforms charge their orchestration fee on top of the STT, LLM, TTS and telephony costs. They are often cheaper overall for small teams, because building reliable turn-taking, interruption handling, call transfer and monitoring takes months of engineering. Self-building usually pays off at tens of thousands of minutes per month.

How can I reduce voice agent costs?

Use a cheaper TTS voice for routine calls, keep the system prompt short and cached, pick a fast mid-tier LLM instead of a flagship, end calls promptly, and negotiate volume pricing once you pass ~100K minutes per month.