Sold by: Vapi
Deployed on AWS
AWS Free Tier
Vapi lets developers build, test and deploy voice agents in minutes rather than months.
Overview
This product helps developers to use a prebuilt robust & scalable infrastructure for integrating voice AI. Using Vapi APIs, developers can deploy conversational voice bots within a few days.
Highlights
- One click onprem deployment
- Highly customisable. Quickly try out and use various LLM, TTS, STT models
Details
Sold by
Categories
Delivery method
Delivery option
2 kubernetes clusters
Latest version
Operating system
Ubuntu 20.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/unit |
|---|---|
Total number of minutes engaged on call | $0.05 |
Dimensions summary
You pay based on usage, measured by the total number of minutes engaged on a call. There is one pricing dimension, so your cost scales directly with call volume. The more minutes your voice agents run, the more you pay. This is a pay-as-you-go structure with no fixed tiers or instance sizes to choose from. Costs rise or fall with your actual call activity each billing period.
Top-of-mind questions for buyers
You are billed for the total minutes your voice agents spend engaged on calls. Each active call minute adds to your total. A voice agent combines speech-to-text, a language model, and text-to-speech to hold conversations. The minutes reflect the time spent handling that live conversation.
The per-minute charge covers hosting for your voice agents. Model provider costs for speech-to-text, language processing, and text-to-speech are separate. Those are charged at cost, or at no added cost when you supply your own provider API key. Network transport is charged by the provider, not by this listing.
Your cost tracks actual call minutes. When agents are not on calls, no per-minute charges accrue. Costs rise and fall with real call activity each billing period. There are no fixed instance sizes or reserved capacity to pay for during quiet periods.
vapi.ai+1
Helpful?
Vendor refund policy
We do not currently support refunds, but you can cancel at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
2 kubernetes clusters
Cloudformation launches a t3 medium instance and a s3 bucket. The ec2 instance, runs some code on launch as part of the user data script. This is broadly what the steps look like in the script: 1. Pull code and artifacts from vapi's s3 url and keep it in ec2 instance, then immediately upload them to the newly created s3 bucket. 2. Pull a pulumi code from vapi' s3, and run it to setup 2 eks clusters. One is for database that uses 2 ec2 instances, and the other actually runs our backend application.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
Initial release for VAPI backend
Additional details
Usage instructions
Access the VAPI dashboard at https://dashboard.subdomain.domain . Everything should be setup for you at this point
Resources
Vendor resources
Support
Vendor support
Please allow 24 hours
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Vonage Voice API is a carrier-grade, programmable voice platform for embedding high-quality PSTN, SIP, and WebRTC calling into any application. Build IVRs, AI voice bots, in-app calling, and automated notifications with , global reach across 227 countries, and AWS integration including Amazon Nova Sonic.
Vonage Voice API is a cloud-native, programmable voice solution built on a reliable, high-quality global carrier network. It enables businesses and developers to design, deploy, and scale custom voice experiences, from simple outbound notifications to sophisticated AI-driven conversational agents, without managing telephony infrastructure.
Enhance customer interactions with SunDevs' Bespoke AI Voice Assistant Development Service. Our service leverages AWS serverless technologies like Lambda, API Gateway, Step Functions and Amazon Bedrock to build scalable, secure AI voice solutions fully integrated with your existing systems.
Pipecat Cloud is enterprise voice AI built on open source. A managed service to host and scale conversational voice agents and multimodal AI, Pipecat Cloud is purpose-built for Pipecat, the most widely used realtime orchestration framework. It makes it easy for developers to build custom voice agent workflows, at ultra-low latency.
Deepgram is the leading voice AI platform for enterprise use cases, offering speech-to-text (STT), text-to-speech (TTS), and full speech-to-speech (STS) capabilities. 200,000+ developers build with Deepgrams voice-native foundational models due to our unmatched accuracy, low latency, and pricing. Having processed over 50,000 years of audio and transcribed over 1 trillion words, there is no organization in the world that understands voice better than Deepgram.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.