---
title: "Vapi alternatives"
description: "Compare Vapi with Speko Agents, Retell AI, Synthflow, Pipecat and LiveKit Agents. See telephony, pricing and who runs the agent, with sources."
canonical: "https://speko.com/vapi-alternatives"
last-updated: "2026-11-10"
---

> ## Speko page index
> The complete index of every page on this site is at: https://speko.com/llms.txt
> Read it before exploring further. It lists the exact Markdown URL for every canonical HTML page.

# Vapi alternatives

Vapi and five alternatives, compared on telephony, pricing and who runs the agent. Two of them, Speko Agents and Speko Router, are ours, and we describe them ourselves.

Short answer

The hosted alternatives are Speko Agents ($0.09 per minute with speech-to-text, LLM and text-to-speech included), Retell AI and Synthflow. The build-it-yourself alternatives are Pipecat and LiveKit Agents. Vapi itself lists $0.05 per minute Vapi hosting, pre-paid, with models passed through at cost on top.

**By**

Speko engineering

**Published**

August 7, 2026

**Updated**

November 11, 2026

## Which alternative for which team?

- ### Which Vapi alternative includes the models in its per-minute price?
  
  - Speko Agents ours
  
  **Why**
  
  Speko Agents lists $0.09 per minute with speech-to-text, LLM and text-to-speech included, plus carriage on Speko numbers. Vapi lists $0.05 per minute Vapi hosting, pre-paid, with model usage passed through on top.
- ### Which Vapi alternative prices each part of the call?
  
  - Retell AI
  
  **Why**
  
  Retell AI lists $0.07 to 0.31 per minute for AI voice agents, assembled from voice infrastructure, text-to-speech, LLM and telephony components.
- ### Which Vapi alternative is best for calls in several languages?
  
  - Speko Agents ours
  
  **Why**
  
  Speko Agents holds up to four languages per agent and switches when the caller does. Each language uses its own speech-to-text, LLM and text-to-speech, chosen from Speko's independent benchmark of speech models by language.
- ### Which Vapi alternative fits a team that buys on an annual contract?
  
  - Synthflow
  
  **Why**
  
  Synthflow sells annual enterprise agreements scoped to call volume and phone system, with launch support where the agreement includes it. Its pricing page lists no rate by the minute.
- ### What if my team wants to own the runtime instead?
  
  - Pipecat
  - LiveKit Agents
  - Speko Router ours
  
  **Why**
  
  Move to Pipecat or LiveKit Agents for the conversation loop, and add Speko Router inside it for benchmark-ranked speech and language models.

[Get started free](https://platform.speko.ai/sign-in) [Book a demo](https://speko.com/book)

## How do the Vapi alternatives compare?

| Option | Who runs the agent | Published price | Phone calls | How you buy |
| --- | --- | --- | --- | --- |
| Vapi the baseline | Vapi hosts it | $0.05/min Hosting only; models billed at cost on top | Connected and billed separately | Self-serve, pay as you go |
| Speko Agents (hosted) our product | Speko hosts it | $0.09/min Speech-to-text, LLM and text-to-speech included | Included: Speko numbers or your SIP trunk | Self-serve, no contract |
| Retell AI | Retell hosts it | $0.07 to $0.31/min Range set by the components you choose | Retell carrier or custom SIP, priced separately | Self-serve, no platform fee |
| Synthflow | Synthflow hosts it | No published rate Annual enterprise agreement; no rate by the minute | Synthflow telephony, Twilio or SIP | Annual enterprise agreement |
| Pipecat | Your team runs it, or Pipecat Cloud | Open source; you pay your own providers | The transport your app picks | Open source |
| LiveKit Agents | Your team runs it, or LiveKit Cloud | $0.01/min Agent hosting only; models billed on top | LiveKit SIP and Cloud numbers | Open source; Cloud plans from $0 |
| Speko Router + Gateway our product, model layer only | Your runtime; Speko routes the models | $0.09/min on Speko infra, or +5% on your provider's rate | Stays with your runtime | Self-serve, no contract |

## What do Vapi and the alternatives cost?

- Speko ours
  
  Speech-to-text, LLM and text-to-speech included
  
  $900 $0.09/min
- Vapi
  
  Hosting only; models billed at cost on top
  
  $500 $0.05/min
- Retell AI
  
  Range set by the components you choose
  
  $700 to $3,100 $0.07 to $0.31/min
- Synthflow
  
  Annual enterprise agreement; no rate by the minute
  
  No published rate
- LiveKit Cloud
  
  Agent hosting only; models billed on top
  
  $100 $0.01/min
- Twilio ConversationRelay
  
  Speech relay only; voice minutes and your LLM on top
  
  $700 $0.07/min

Monthly figures use the published per-minute rate only. They leave out plan fees, phone numbers, carriage and any models a vendor bills on top.

## How do I switch from Vapi to Speko?

1. ### 1Connect an agent to Speko
   
   Add Speko's MCP server to Claude Code, Cursor or Codex. [Set up Claude Code](https://speko.com/integrations/claude-code) [Set up Cursor](https://speko.com/integrations/cursor) [Set up Codex](https://speko.com/integrations/codex)
2. ### 2Convert your Vapi agent
   
   Ask it to convert your Vapi config. The MCP server reads it and drafts a Speko agent for you to review.
   
   [How the conversion works](https://docs.speko.ai/quickstart/mcp)
3. ### 3Bring your number
   
   Import your number over a SIP trunk, or buy a Speko number.
   
   [Phone number setup](https://docs.speko.ai/guides/phone-agents)
4. ### 4Test, then go live
   
   Run simulated callers against the draft. Deploy when the checks pass.
   
   [How testing works](https://speko.com/voice-agent-testing)

## The alternatives, one by one

[Get started free](https://platform.speko.ai/sign-in) [Book a demo](https://speko.com/book)

You get $5 in credit when you sign up. Calls then cost $0.09 per minute.

## Notes

- Vendor facts are from each vendor's own pages, linked in the tables, checked November 10, 2026.
- Prices are from each vendor's own pricing page, checked November 11, 2026.
- Speko Agents facts are from the Speko docs and pricing page, checked November 11, 2026.
- Speko measures models and does not rank platforms. The benchmark snapshot behind Speko routing is at [speko.com/benchmarks/data.json](https://speko.com/benchmarks/data.json).

Related

- [Voice agent platforms, runtimes and model routers](https://speko.com/voice-agent-platforms)
- [Retell AI alternatives](https://speko.com/retell-alternatives)
- [Synthflow alternatives](https://speko.com/synthflow-alternatives)
- [Speko vs Vapi](https://speko.com/speko-vs-vapi)
- [Voice agent testing](https://speko.com/voice-agent-testing)
- [Multilingual voice agents](https://speko.com/multilingual-voice-agents)
- [Voice agents by business](https://speko.com/solutions)
- [Speko pricing](https://speko.com/pricing)
