Put your ElevenLabs agent on live Amazon Connect calls - it works like a real team member: in your queues, supervised and reported like any agent. No SIP.
ElevenLabs Voice Agent puts your ElevenLabs conversational agent on live Amazon Connect calls - natural and interruptible - with a native human handoff, all without leaving your contact centre.
Why not the ElevenLabs SIP path? The ElevenLabs SIP integration pulls the call out of Connect, splitting the contact record and breaking native human handoff, Contact Lens, and metrics. LiveUCX keeps your agent native - it runs inside your own Amazon Connect instance and operates as an agent, on one contact record with the conversation context passed along.
Works as a real member of your team. Because it operates as an agent in your own Amazon Connect instance - not a bolt-on - your ElevenLabs voice inherits everything your human team already has, with no new tooling and no separate console:
Sits in your queues. Routed contacts like any other agent; move it in and out of queues on demand.
Supervise it like a team member. Silent monitor, whisper, and barge-in - listen in or jump onto the call.
Native Connect features, for free. Call recording and Contact Lens sentiment analysis, and warm or cold transfers - to a human, another queue, or a Quick Connect - with context passed along.
Elastic capacity. Spin agents up as overflow when call volume spikes, then scale back after - handle surges without hiring.
Always on. 24/7, never takes a break: no after-call-work fatigue, no shrinkage, always Available.
Fully visible in reporting. It appears in Amazon Connect real-time and historical and live reports - contacts handled, handle time, and more - managed exactly like your people.
Proven live. Hear it for yourself - our Tom demo agent answers, converses, and hands off. Dial +61 7 3905 7328.
Residency, stated plainly. ElevenLabs runs offshore (no Australian point of presence) - disclosed. If you need speech to stay in Australia, use our multi-provider Live AI Agent listing with the Deepgram Australian endpoint.
Simple, honest pricing. You pay one per-active-agent monthly fee for the LiveUCX platform only. You bring your own ElevenLabs account and pay ElevenLabs directly for voice, plus your own Amazon Connect telephony - no markup on AI minutes, your own ElevenLabs rates, full cost control. There is no long-term commitment - simple pay-as-you-go, billed monthly.
Get started with a self-serve wizard: connect your Amazon Connect instance, add your ElevenLabs key, pick your agent.
Highlights
Your ElevenLabs voice works as a real member of your team - it operates as an agent in your Amazon Connect contact centre: in your queues, supervised (monitor, whisper, barge-in), and reported like any agent. No SIP, no split record.
Every native Connect feature comes free - call recording, Contact Lens sentiment, warm or cold transfers and Quick Connects with context, and a native human handoff on one contact.
Elastic, 24/7 capacity - spin agents into queues as overflow during peaks and scale back after. Proven live (dial the Tom demo). Pay ElevenLabs direct, no markup. No long-term commitment.
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 follows a usage model based on how many voice agents you run each month. You can pay per active AI agent, billed monthly for each concurrent voice agent in Amazon Connect. Two fixed monthly bundles are also available: one covers up to 5 voice agents, and one covers up to 20. The bundles charge a set monthly price regardless of how many agents within that cap you use. This lets you scale from a single agent to larger volumes by choosing the option that matches your expected agent count.
Top-of-mind questions for buyers
What counts as one active AI agent for billing?
One active agent is a single concurrent ElevenLabs voice agent running in your Amazon Connect contact flow. It answers calls, holds a conversation, and hands off to a human queue. Billing counts each concurrent voice agent, per active agent, per month.
How does the per-agent option differ from the 5-agent and 20-agent bundles?
The per-agent option charges monthly for each concurrent voice agent you run. The bundles charge one fixed monthly price for a set cap: up to 5 agents or up to 20. Bundles suit predictable agent counts; per-agent billing suits running a single agent.
If I run fewer agents than my bundle cap, does the price drop?
No. Each bundle charges a fixed monthly price regardless of how many agents you use within its cap. The up-to-5 and up-to-20 bundles bill the same set amount whether you run one agent or fill the cap.
www.proucx.com
Helpful?
Vendor refund policy
ElevenLabs Voice Agent for Amazon Connect is billed monthly in arrears for actual usage (active agents metered through AWS Marketplace), so there are no upfront or prepaid fees to refund. If you believe you were billed in error, email support@proucx.com.au within 30 days of the invoice with your AWS account ID and the billing month. We will investigate and, where an error is confirmed, issue a correction or refund through AWS Marketplace.
How can we make this page better?
Tell us how we can improve this page, or report an issue with this product.
Give us feedbackReport a problem with this product or seller
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.
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Email support Monday to Friday during Australian business hours (AEST); response within one business day. Product documentation and contact form at proucx.com/support.
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.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the nova-3 model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0077/min as described by https://deepgram.com/pricing. Private pricing available upon request.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the nova-3 model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0092/min as described by https://deepgram.com/pricing. Private pricing available upon request.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
zeb’s integration of ElevenLabs with Amazon Connect delivers multilingual, hyper-realistic Virtual AI Agents powered by generative speech and agentic AI. Support 30+ languages, clone custom voices, trigger real-time actions, and retain full native Amazon Connect features including Contact Lens, call recording, and agent transfer.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the aura-2 model which can each speak a set of languages and voices. See version details for more information. Deepgram charges are billed per request as described by https://deepgram.com/pricing
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the flux model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0078/min as described by https://deepgram.com/pricing.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
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.