Voicegain is excited to announce the launch of Voicegain Casey, a payer focused AI Voice Agent that transforms the end-to-end call center experience with the power of generative AI. Voicegain Casey is a software suite of the following three Voice AI SaaS applications that helps a health plan or TPA call center improve operational efficiency and increase the CSAT and NPS (Net Promoter Score):

A. Voicegain Casey - Suite of Generative AI-Powered SaaS Applications

1. AI Voice Assistant:

The AI Voice Assistant replaces a touch-tone IVR with a modern LLM-powered conversational AI Phone Agent. The AI Phone Agent can answer all calls that are received at a Health Plan or TPA Call center. It engages callers in a natural conversation and automates routine telephone calls like Claims Status, eligibility inquiries and eligibility verifications. In our experience, there is a very compelling business case to automate provider phone calls in Health Plan and TPA call centers and Voicegain Casey is specifically designed to do this. The AI Voice Assistant is also trained to perform HIPAA Validation and triaging of calls. So if the AI has not been trained to answer a specific question, it routes the call to the call center for live assistance.

2. AI Co-Pilot: 

Voicegain AI Co-Pilot is a browser extension that runs as a browser side-panel of Call Center Agent's CRM. The Co-Pilot is integrated with the Contact Center/CCaaS platform of the Payer. When a call transferred by the AI Voice Assistant is eventually answered by a Live Agent, all the information collected by the AI Voice Assistant is presented as a "Screen-Pop" on the Desktop of the Live Agent (also referred to as CTI). This CTI/Screen pop feature ensures that the front-line call center staff do not have to ask the customer to repeat any information that was provided to the AI Voice Assistant. In addition to the Screen-Pop, the AI Co-Pilot also guides the front-line call center staff in real-time by listening, transcribing and analyzing the conversation and providing real-time guidance . The AI Co-Pilot also generates a summary of the conversation within five seconds of the completion of the call. This automated summarization easily saves 1-2 mins of wrap-up time or after call work which is very common in these health plan and TPA call centers.

3. AI QA & Coach:

Voicegain AI QA & Coach is a browser-based AI SaaS application that is used by Team-leaders, QA Call Coaches/Analysts and Operations Managers in a call center. This AI SaaS app can record and measure the sentiment of the callers, analyze the QA score and provided automated coaching tips to the Agents. Voicegain uses the latest open-source reasoning LLMs (like LLAMA 3, Gemma) and closed-source reasoning models like o-3 from Open AI. With the power of modern reasoning models, almost the entire QA score-card (at least 80% of the questions) can be easily answered with modern reasoning-based LLM models. This SaaS App also provides a database of all whole-call-recordings of the entire conversation of the customer - which includes the AI Voice Assistant part, the transfer to the specific Call Center queue and eventually the entire conversation between the Live Agent and the Caller.

‍

B. Integrations

Voicegain Casey requires the following 3 key integrations to help with automation and real-time assistance.

1. Contact Center Platform/CCaaS Platform

Voicegain Casey integrates with modern CCaaS platforms. Current Integrations include Aircall, Five9, Genesys Cloud. Planned integrations include Ringcentral, NICE CXOne and Dialpad.

2. CRM Software

Voicegain Casey integrates with the CRM software of the Health plan or the TPA. This can be an off-the-shelf CRM like Zendesk or Saleforce. It can also be a proprietary/homegrown CRM. As long as the CRM is a browser-based SaaS application, this should not be an issue. Voicegain Casey AI Co-Pilot is a browser-extension that is installed in the side-panel of the same browser tab as the CRM. At the end of the call, the summary of the call is automatically generated and available on the browser extension within 5 seconds of the end of the call.

3. Eligibility & Claims

Voicegain Casey needs access to the member data (for HIPAA Validation) and claims data.

C. Demo and Additional Information

For further information on Voicegain casey, including a demo, please visit this link

D. Give us a shout!

If you would like to understand Voicegain Casey in more detail or if you would prefer a detailed product demo over a Zoom video call, please do not hesitate to send us an email. You can reach us at sales@voicegain.ai or support@voicegain.ai

‍

Voicegain, the leading Privacy-first Voice AI platform for enterprises and AI SaaS companies, is thrilled to announce the successful completion of a System and Organizational Control (SOC) 2 Type 2 Audit performed by Johanson LLP. This achievement underscores Voicegain's ongoing commitment to the highest standards of security, availability, and confidentiality for customer data.

Developed by the American Institute of Certified Public Accountants (AICPA), the SOC 2 Information security audit provides a report on the examination of controls relevant to the trust services criteria categories covering security, availability, processing integrity, confidentiality, and privacy. Voicegain’s SOC 2 Type 2 report did not have any noted exceptions and was therefore issued with a “clean” audit opinion from Johanson LLP. The SOC 2 Type 2 certification is widely recognized as a rigorous measure of an organization’s systems and controls over an extended period.

"As a Privacy first Voice AI Platform, data protection and trust are at the heart of Voicegain. Whether you are a developer working for a startup using our APIs or a Fortune 500 enterprise user of our platform, you shouldn’t have to worry about the controls in place for your sensitive voice data. It has been close to 2 years since we embarked on our SOC 2 Type 1 journey and I am really proud of what our team has accomplished. We look forward to providing businesses worldwide with Voice AI solutions that deliver true peace of mind when it comes to security and compliance" said Dr Jacek Jarmulak, Co-founder, CTO & CISO Of Voicegain.

What Is SOC2 Type 2?

Service Organization Control 2(SOC2) is a set of criteria established by the American Institute of Certified Public Accountants (AICPA) to assess controls relevant to the security, availability, and processing integrity of the systems a service organization uses to process users’ data and the confidentiality and privacy of the information processed by these systems. SOC 2 compliance is important for Voice AI platforms like Voicegain, as it demonstrates that we have implemented controls to safeguard users’ data.

There are two types of SOC 2 compliance:

1. SOC 2 Type 1: Validates that an organization has established appropriate controls at a specific point in time. Voicegain's successful audit established this as of Jul 14 2023.
2. SOC 2 Type 2: Confirms that an organization has maintained and operated those controls over a period of time, typically 6 to 12 months. Voicegain's latest report covers this for the period July 2024 to Jan 2025.

Implications for Voicegain Users

From a functional standpoint, achieving SOC 2 Type 2 compliance doesn’t change anything. Our APIs and Apps will work exactly as they always have and as expected. However SOC 2 Type 2 compliance means that we have established a set of controls and processes to ensure the security of our users’ data. This compliance demonstrates that we have the necessary measures in place to protect sensitive information from unauthorized access and disclosure.

What’s Next? Increasing the Maturity of our security process

Our commitment to security doesn’t end with SOC 2 Type 2. We are looking forward to increasing the maturity of the entire security process. This includes the following:

• Establishing a Continuous Security Monitoring Program
  • Tools and processes for ongoing detection and response (SIEM, SOC, endpoint protection).
• Developing an Incident Response and Business Continuity Culture
  • Regular tabletop exercises, disaster recovery drills, and documented processes.
• Hardening Third-Party Risk Management
  • Vendor risk assessments, contract language, and ongoing monitoring of partners’ security posture.
• Security Awareness and Training
  • Regular phishing simulations, role-based security training, and compliance training to ensure staff remain vigilant.
• Adopting a “Privacy by Design” Mindset
  • Integrate privacy considerations early in every new product or feature development cycle.

"We understand that in today's fast moving industry landscape, data security is non-negotiable," added Arun Santhebennur, Co-founder & CEO of Voicegain. "By achieving SOC 2 Type 2 compliance, we aim to set a high watermark in the Voice AI market. Our customers can have full confidence that their sensitive information is protected throughout its lifecycle."

To request a copy of our SOC 2 Type 2 report, please email security.it@voicegain.ai

‍

This article outlines how the modern Voicegain deep-learning based Speech-to-Text/ASR can be a simple and affordable alternative for businesses that are looking for a quick and easy replacement to their on-premise Nuance Recognizer. Nuance has announced that its going to end support for Nuance Recognizer, its grammar-based ASR which uses the MRCP protocol, sometime in 2026 or 2027. So organizations that have a Speech-enabled IVR as their front door to the contact center need to start planning now.

The future belongs to Generative AI powered Voice Agents

With the rise of Generative AI and highly accurate low latency speech-to-text models, the front door of the call center is poised for major transformation. The infamous and highly frustrating IVR phone menu will be replaced by Conversational AI Voicebots; but this will likely happen over the next 3-5 years. As enterprises start to plan their migration journey from these tree-based IVRs to an Agentic AI future, they would like to do this on their timelines. In other words, they do not want to be forced to do this under the pressure of a deadline because of EOL of their vendor.

Staying On-Premise or in a VPC for both the IVR platform and the ASR

In addition, the migration path proposed by Nuance is a multi-tenant cloud offering. While a cloud based ASR/Speech-to-Text engine is likely to make sense for most businesses, there are companies in regulated sectors that are prevented from sending their sensitive audio data to a multi-tenant cloud offering. 

In addition to the EOL announcement by Nuance for their on-premise ASR, a major IVR platform vendor like Genesys has also announced that its premise-based offerings - Genesys Engage and Genesys Connect - will also approach EOL at the same time as the Nuance ASR.

So businesses that want a modern Gen AI powered Voice Assistant but want to keep the IVR on-premise in their datacenter or behind their firewall in a VPC will need to start planning very quickly what their strategy is going to be.

At Voicegain, we allow enterprises that are in this situation and want to remain on-premise or in their VPC with a modern Voicebot platform. This Voicebot platform runs on modern Kubernetes clusters and leverages the latest NVIDIA GPUs. 

Switching Nuance Recognizer with Voicegain is quick and easy!

Rewriting the IVR Application logic to migrate from a tree-based IVR menu to a conversational Voice Assistant is a journey. It would require investments and allocation of resources. Hence a  good first step is to simply replace the underlying Nuance ASR (and possibly the IVR platform too). This will guarantee that a company can migrate to a modern Gen-AI Voice Assistant on its timelines.

Voicegain offers a modern highly accurate deep-learning-based Speech-to-text engine trained on hundreds of thousands of hours of telephone conversations. It is integrated into our native modern telephony stack. It can also talk over the MRCP protocol with VoiceXML based IVR platforms and it supports the traditional Speech grammars (SRGS, JJSGF). Voicegain also supports a range of built-in grammars (like Zipcode, Dates etc).

As a result, it is a simple "drop-in" replacement to the Nuance Recognizer. There is no need to rewrite the current IVR application. Instead of pointing to the IP address of the Nuance Server, the VoiceXML platform just needs to be reconfigured to point to the IP address of the Voicegain ASR server. This should take no more than a couple of minutes.

Voicegain Telephony Bot API - a Callback API for Telephony-based AI Voice Assistant

In addition to the Voicegain ASR/STT engine, we also offer a Telephony Bot API. This is a callback style API that includes our native IVR platform and ASR/STT engine can be used to build Gen AI powered Voicebots. It integrates with leading LLMs - both cloud and open-source premise based - to drive a natural language conversation with the callers.

Talk to us about your IVR migration journey!

If you would like to discuss your IVR migration journey, please email us at sales@voicegain.ai . At Voicegain, we have decades of experience in designing, building and launching conversational IVRs and Voice Assistants.

Here is also a link to more information. Please feel free to schedule a call directly with one of our Co-founders.

Nuance just announced that the Nuance Recognizer which is a MRCP grammar-based ASR will reach EOL in May 2027. This decision affects a significant number of on-premise speech-enabled IVR systems that rely on the Nuance Recognizer, creating uncertainty for many businesses.

If you are impacted by this decision, this post outlines an immediate fix while preparing companies for an AI future.

Why is Nuance Ending Support for Recognizer?

The decision appears to be driven by two primary factors:

1. Transition to Modern AI Solutions: Traditional grammar-based speech recognition is being replaced by large-vocabulary Speech-to-Text (STT) systems, which are better suited for the era of AI-powered phone agents. These systems enable natural, conversational interactions, making them far superior to decision-tree-based IVRs.
2. Shift to Cloud-Based Platforms: Contact center vendors are migrating their solutions to the cloud, leaving behind older protocols like MRCP (used for on-premise VoiceXML-based IVRs). Modern STT offerings, such as those from Google and Nuance, use gRPC protocols, signaling a move toward cloud-native solutions.

Nuance’s Upgrade Options May Not Work

Nuance provides two upgrade options, but neither is fully compatible with existing IVRs:

1. Cloud-Based Grammar Recognizer: While this option supports grammars, it uses a gRPC-based API that is incompatible with VoiceXML-based IVR platforms.
2. Large-Vocabulary STT: Designed for conversational AI voice bots, this option requires a complete app rewrite to utilize conversational AI—making it a more time-intensive and expensive solution.

Challenges for Businesses

The EOL announcement introduces two major hurdles for businesses:

1. Costly App Rewrites: Transitioning to AI-powered phone agents requires a complete rewrite of IVR applications, which can be expensive. Many businesses are reluctant to undertake this on Nuance's timeline.
2. On-Premise Feature Gap: While cloud solutions offer many advantages, businesses with strict privacy and control requirements often prefer modern features in on-premise contact center environments.

If your business relies on Nuance’s MRCP-based ASR (as of November 2024), now is the time to plan for a replacement. Below, we outline a solution that allows you to continue using your existing IVR without major disruptions.

Voicegain MRCP ASR as "drop-in" replacement for Nuance MRCP ASR

Voicegain offers a seamless alternative to Nuance's grammar-based MRCP ASR. Our platform:

• Supports Existing IVR Apps: Voicegain natively supports traditional SRGS/grXML grammars and MRCP (versions 1 and 2). Your current VoiceXML-based IVR can continue running without changes.
• Simple Replacement: Switching to Voicegain is as easy as updating your IVR to point to our ASR server instead of Nuance’s—just replace the IP address of Nuance with that of Voicegain ASR in the VoiceXML platform configuration settings.

This allows you to maintain your current IVR workflow until you're ready to upgrade on your terms.

Future-Proof with Agentic AI

Over the next few years, many businesses will transition to generative AI-powered phone agents to improve caller experiences and increase automation rates. While this is a promising future, businesses shouldn’t feel forced to move to the cloud just to access these capabilities.

Voicegain’s deep-learning-based large-vocabulary STT engine is designed to evolve with your needs:

• Scalable and Flexible: Built using NVIDIA GPUs for high-throughput processing, our platform also supports CPU-optimized deployment in containerized environments for smaller workloads.
• Future-Ready: When you decide to build a Gen-AI-powered phone agent, Voicegain’s STT engine will be ready to integrate into your existing tech stack.

‍Test this today

To discuss your upgrade options, email us at sales@voicegain.ai. If you'd like to test our solution, sign up for a free developer account (no credit card required) and get 1,500 free hours of usage. Visit the link in the instructions, and once signed up, contact support@voicegain.ai to request MRCP access.

Start future-proofing your IVR system today with Voicegain.

‍

‍

This articles provides an overview of Voicegain SIP Media Stream Back-to-Back User Agent (B2BUA), a Contact Center Platform agnostic solution that forks real-time SIP media streams from premise-based contact centers to Voicegain Speech-to-Text for real-time transcription. In SIP telephony, B2BUA stands for Back-to-Back User Agent and is a specific network element that can both terminate and originate media streams. This is explained further in this post.

The Voicegain SIP Media B2BUA is a containerized solution that is deployed in the same network as the Contact Center platform. Once configured, Developers or enterprise customers can get real-time access to speaker-separated transcripts (over a Websocket connection). 

The Voicegain SIP Media B2BUA is a solution for enterprises and SaaS ISVs looking to extend their real-time LLM-powered Voice AI application to premise-based contact centers. Examples of such on-premise contact center platforms include Avaya, Genesys or Cisco. The Generative Voice AI applications supported include Real-Time Agent Assist or Voice AI Co-Pilots, Real-time sentiment analysis, voice biometrics and other types of real-time speech analytics apps.

The Challenge: Accessing Real-time voice data from On-Prem Call Centers is hard

Most premise-based Contact Center platforms - whether it is from Avaya, Genesys, or Cisco - do not provide programmatic access to real-time media streams. While these systems are reliable for call routing and management, they were not designed for modern LLM-powered AI applications.

Traditionally forking of media streams is supported by a Session Border Controller (SBC), a separate network element that sits "in front" of the Call Center platform. These SBCs rely on a protocol called SIPREC to fork these media streams. However SIPREC is primarily intended for network-based compliant call recording and commercial compliant recording vendors like NICE or Verint leverage the SIPREC protocol to access real-time media streams from premise-based contact center platforms.

However there are many pain points :

1) Only large enterprises have implemented Session Border Controllers.

2) Even if an enterprise has an SBC, the forking media capacity is used up by the call recording solution. Adding an additional streaming option for generative AI requires upgrades to hardware and software licensing on the SBC.

The Solution: Voicegain SIP Media Stream B2BUA

Voicegain offers a highly scalable, reliable and fully contained SIP Media Stream B2BUA to address the challenge discussed above. This B2BUA is a containerized network element that is deployed in the same network as the premise-based contact center. From a SIP Protocol standpoint, this Media Stream Back-to-Back User Agent (B2BUA)  acts as a transparent media relay while forking SIP RTP media streams to real-time Speech-to-Text.

What is a B2BUA? Unlike a simple SIP proxy that only handles signaling, a Back-to-Back User Agent terminates and re-originates both signaling and media streams, allowing it to manipulate call flows while maintaining access to the audio content.

Key Components and Architecture

The Voicegain SIP Media Stream B2BUA is:

• Containerized: Deployed via Docker Compose in your existing network
• Platform-agnostic: Works with Avaya, Cisco, Genesys, and other SIP-based platforms
• Lightweight: Minimal processing overhead with efficient media handling
• Non-disruptive: Integrates with existing call flows through simple SIP routing

The diagram above show cases the call flow to fork media streams for real-time transcription.

At a high-level, most SIP-based Contact Center ACDs like Avaya Communication Manager, Genesys Engage and Cisco UCCE support creation of SIP Trunks. The Voicegain SIP Media Stream B2BUA is a SIP Server/SIP Peer that connects to the premise-based ACD over a dedicated SIP trunk. It can receive calls from and make calls to the premise-based ACD.

The overall call flow has the following steps:

1. Install the Voicegain Media Stream B2BUA as a containerized local network element (using Docker Compose).
2. Create a local SIP Trunk on the ACD and test using the SIP Trunk to make calls to and receive calls from the VG Media Stream B2BUA.
3. Configure ACD to transfer incoming calls first to the VG Media Stream B2BUA over SIP (This is essentially a SIP INVITE of the Media Stream B2BUA). Include the DID or URI of the Contact Center Queue or the IVR in the routing label (SIP URI). (Step 1)
4. VG Media Stream B2BUA has an associated configuration file. This provides any mapping required of the destination DID.
5. Based on the above, the B2BUA "bridges" the DID (or URI) of the Contact Center Queue or the IVR with the incoming call(Step 2)
6. The B2BUA also forks the RTP streams of the 2-channel stereo audio (of the caller and the agent) to Voicegain STT for transcription (Step 3)
7. The real-time transcript is made available on a Websocket connection to the Gen AI App (Step 4)

To summarize, what is needed is to configure a SIP Trunk on the current Contact Center ACD and use that to transfer calls to Voicegain Media Stream B2BUA (which is the equivalent of initiating a SIP INVITE). The Medial Stream SIP B2BUA in turn bridges the DID of the Contact Center Queue or IVR (which is a SIP INVITE to the destination SIP URI) over the same SIP Trunk and then forks the two RTP streams (caller & Agent) to Voicegain STT.

Tested with Avaya

The Voicegain SIP Media Stream B2BUA has been deployed in production application for a leading health care customer with an On-Premise Avaya Contact Center. 

Implementation Requirements

To deploy the Voicegain SIP Media Stream Proxy, you'll need:

1. A Docker-compatible server within your contact center network
2. SIP connectivity to your existing contact center platform
3. Network access to Voicegain's Speech-to-Text APIs (or on-premises deployment)
4. Basic configuration to define routing rules and destination mappings

Contact Us to discuss your application

If you have an on-premise contact center and you would like to discuss getting access to the real-time media stream, please contact us at support@voicegain.ai

‍

This article outlines the evaluation criteria involved in selecting a real-time Speech-to-Text or ASR  for LLM-powered AI Copilots and Real-time agent assist applications in the contact center. This article is intended for Product Managers and Engineering leads in Contact Center AI SaaS companies and CIO/CDO organizations in enterprises that are looking to build such AI co-pilots.

The buzz around Gen AI-powered Co-Pilot & Realtime Agent Assist  

A very popular use-case for Generative AI & LLMs is the AI Co-pilot or Realtime Agent Assist in contact centers. By transcribing an agent-customer conversation in real-time and feeding the transcript to modern LLMs like Open AI's GPT, Facebook's LLAMA2 or Google's Gemini, contact centers can guide their agents to handle their calls more effectively and efficiently.

An AI Co-pilot can deliver great business benefits. It can improve CSAT and NPS as the AI can quickly search and present relevant knowledge-base to the agent, enabling them to be more knowledgeable and productive. It can also save Agent FTE costs by reducing AHT and eliminating wrap time.

In addition by building a library of "gold-standard" calls across various key call types, LLM can also deliver personalized coaching to agents in an automated way using Generative AI.Companies are finding that while Gen AI-powered Co-Pilots are especially beneficial to new hires, they also deliver benefits to agents with tenure too.

Building an AI-powered Co-Pilot requires three main components - a) A real-time ASR/Speech-to-Text engine for transcription 2) An LLM to understand the transcript and 3) Agent and Supervisor/Manager facing web applications. The focus of this blog post is on the first component - the real-time ASR/Speech-to-Text engine.

Now here are the four key factors that you should look at while evaluating the real-time ASR/Speech-to-Text engine.

1. Ease of Integration with Audio Source

The first step for any AI Co-Pilot is to stream the agent and customer real-time media to an ASR that supports streaming Speech-to-Text. This is easily the most involved engineering design decision in this process.

There are two main approaches  - 1) Streaming audio from the server-side. In an enterprise contact center, that would mean forking the media from either an enterprise Session Border Controller or the Contact Center Platform (which is the IP-PBX). 2) Streaming audio from the client side - i.e from the Agent Desktop. An Agent desktop can be a OS based thick client or a browser-based thin client - this depends on the actual CCaaS/Contact-Center platform being used.

Selecting the method of integration is an involved decision. While there are advantages and disadvantages to both approaches, server-side approaches have been the preferred option. This is because you would avoid the need to install client software and plan for compute resources at the agent desktop level.

However if you have an on-premise contact center like an Avaya, Cisco or Genesys, the integration can become more involved. This is because each platform has its own mechanism to fork these media streams and you also need to install the ASR/STT behind the corporate firewall (or open it up to access a Cloud-based ASR/STT).

Net-net, there is a case to be made for client-side streaming too - because not all companies may have the expertise available within the company.

There are modern CCaaS platforms like Amazon Connect, Twilio Flex, Genesys Cloud and Five9 that offer APIs/programmable access to the media streams. You are in luck if you have one of these platforms. Also if the PSTN access is through a programmable CPaaS platform - like Twilio, Signalwire, Telnyx etc, then it is quite a

2. Protocol support from the ASR/STT 

Once you finalize a method to fork the audio, you would need to consider the standard protocols supported by the ASR/Speech-to-text engine. Ideally, the ASR/STT engine should be flexible and support multiple options. One of the most common approaches today to stream audio over websockets. It is important to confirm that the ASR/Speech-to-Text vendor supports two-channel/stereo audio submission over websockets. There are other approaches - sharing audio over gRPC and over raw RTP.

3. Speed/ Latency of ASR/Speech-to-Text model

The next big consideration is the latency of real-time ASR/Speech-to-Text model - which in turn depends on the underlying neural network architecture of the model. In order to provide timely recommendations to the Agent, it is important to target ASRs that can deliver word-by-word transcript in less than one second and ideally in about 500 milliseconds. This is because there is additional latency associated with collecting and submitting the transcript to LLMs and then delivering the insights onto the Agent Desktop. 

4. Affordability

Last but not the least, it is really important that the price for real-time transcription is affordable in order to build a strong business case for the AI Co-Pilot. It is important to confirm that the agent and caller channel are not priced independently as that very often kills the business case.

If you are building an LLM-powered AI Co-pilot and would like to engage in a deeper discussion, please give us a shout! You can reach us at sales@voicegain.ai.

‍

‍