Senior Voice AI & Omnichannel Automation Engineer (LiveKit + Vobiz + Sarvam + WhatsApp & Email) -- 2

@Microlent

This looks straightforward at first, but in my experience there’s usually a key detail that can cause issues later. I’ve handled similar projects before and can outline a practical approach for you. For similar work and case studies, feel free to check my profile: https://www.freelancer.com/u/Microlent Let me know if you I'd like me to walk you through the plan. – Rajesh Rolen

@ssquare489

With my extensive experience in building advanced, performant applications integrated with AI, I am uniquely positioned to enhance your SaaS platform. I am quite familiar with the Technical Challenges & Scope of Work outlined in your project description, including optimizing Voice Bots using LiveKit and Vobiz SIP. I can streamline the voice flow to significantly reduce delays for a real-time conversational experience with ultra-low latency. My proficiency in different omnichannel APIs such as WhatsApp Business Cloud API and Metro developer ecosystem makes me an apt fit to handle the bulk messaging features of your platform. The robust technical platform you require demands efficient memory management and my expertise ensures fixing any potential memory leaks and cleaning up stale event listeners. Additionally, I can effectively establish the essential link between backend event metrics and your frontend dashboards for both WhatsApp and Email analytics. While we take on these practical challenges, I remain dedicated to delivering tangible outcomes: near real-time conversational voice latency, solid backend modifications linked to pre-built dashboards, fully operational draft approval toggle infrastructure, refactored backend code and clean implementation documentation—all done without any compromises on quality or deadlines.

@andriii2

Hello, ✨✨✨From Vision to Victory-We Code Your Success✨✨✨ I can help refine your existing React/Node SaaS backend with focused improvements for LiveKit voice latency, barge-in handling, WhatsApp campaigns, email automation, and dashboard metric wiring. For the voice layer, I would move the current flow toward true chunk-streaming using LiveKit Agents, Vobiz SIP, Sarvam STT/TTS, and Groq with proper stream cancellation. On barge-in, I would use VAD/turn-taking events to flush audio buffers, abort in-flight LLM/TTS requests, clear queued utterances, and restart the pipeline cleanly so old responses never replay out of sync. I can also review EventEmitter warnings, stale WebSocket/RTP listeners, and memory cleanup issues to stabilize long-running sessions. For WhatsApp and email, I can connect campaign uploads, outbound delivery events, inbound reply triggers, draft approval mode, and real-time analytics to your existing React dashboards using structured backend events. I have experience with Node.js streams, WebSockets, REST APIs, AI conversation flows, WhatsApp Business API, SMTP/IMAP workflows, and production debugging. My estimate for these backend updates is 12–18 days, depending on current code quality and integration access, within a fair budget range after reviewing the repo. Best Regards

@sgwtechnology

Hi, Your platform aligns well with my expertise in Node.js, Express, real-time streaming architectures, WebSockets, AI integrations, and omnichannel communication systems. Approach: • Audit existing LiveKit/SIP/STT/TTS pipeline and identify latency bottlenecks. • Implement chunk-based streaming, barge-in interruption handling, buffer flushing, and generation cancellation for near real-time responses. • Fix EventEmitter leaks, stale listeners, and synchronization issues. • Integrate WhatsApp Business campaign engine, analytics, and AI-triggered workflows. • Implement bulk email campaigns, draft approval mode, inbound AI conversations, and real-time metrics dashboards. A few questions: • Is the current LiveKit Agent implementation already deployed in production? • What is your current average voice latency? • Which email provider stack are you using (Google, Microsoft, SMTP)? I am ready to start today immediately. Let's discuss now, review the architecture, and create a precise timeline for delivery. Best regards

@azwa04

Hi, I can easily DO your work IN 24 HOURS, DM me now to get started, PRICE NEGOTIABLE 100% Work satisfaction is provided

@mrbhautik

Hello, I have experience building AI-powered applications, automation workflows, dashboards, and API integrations. Recently, I developed and deployed an investment platform with separate User/Admin panels, analytics, and cloud deployment. I have also built AI solutions, automation systems, and production-ready web applications. I can help with Voice AI, omnichannel automation, CRM integrations, workflow automation, API connections, and scalable backend development. My expertise includes Node.js, Python, AI Agents, OpenAI APIs, n8n, automation workflows, and full-stack development. These technologies are commonly used in voice AI, CRM, and omnichannel automation systems.

@mussaibb7

I'd love to dive into this project. A reliable AI workflow with clear inputs, outputs, and fallback behavior is crucial for this omnichannel automated outreach and inbound conversational SaaS platform. This involves designing a robust architecture that integrates multiple channels (LiveKit, Vobiz, Sarvam, WhatsApp, and Email) using Node.js, while ensuring seamless interactions with AI models and LLMs. My primary strength lies in crafting scalable AI solutions, as evident from the Arabic Legal AI Retrieval System I built, fine-tuning LLaMA 3.1 and FAISS retrieval for efficient API delivery. I'm confident that my expertise in modular orchestration, evaluation, and fallback behavior will help bridge the technical gaps in this project. For this project, I plan to deliver modular workflow code, a well-structured config or prompt structure, logging and fallback handling mechanisms, and a README documentation. I'll work closely with you to understand the existing workflow, identify pain points, and clarify scope, first milestones, and critical technical constraints before we begin.

@letswork92

I see that you’re looking to enhance the performance and functionality of your omnichannel SaaS platform, particularly in optimizing real-time voice interactions and integrating bulk messaging capabilities. With over 12 years of experience in full-stack development using Node.js and React.js, I have a deep understanding of the complexities involved in implementing low-latency audio processing with LiveKit and Vobiz. My previous work includes deploying advanced conversational voice bots that leverage similar technologies, where I successfully optimized streaming pipelines and implemented interruption handling mechanisms. I also have hands-on experience connecting real-time analytics from WhatsApp Business API and email systems to intuitive dashboards. To ensure seamless integration of these features, could you clarify if there are specific user scenarios or edge cases you'd like us to prioritize during development? This will help tailor my approach effectively.

@karthikresonite

Hello, Resonite Technologies has a senior team experienced in real-time Voice AI, telephony integrations, Node.js backend optimization, WhatsApp Business API, email automation, and conversational AI platforms. We can enhance your existing React/Express/Node.js SaaS platform by optimizing the LiveKit + Vobiz + Sarvam AI voice pipeline for near real-time latency, implementing true barge-in interruption handling with buffer flushing and generation cancellation, and resolving memory leaks, stale listeners, and audio synchronization issues. Our expertise includes: ✔ LiveKit Agents, SIP, RTP & WebSocket streaming ✔ Sarvam STT/TTS, Groq LLM integration ✔ WhatsApp Business Cloud API campaign engines & analytics ✔ Bulk email automation via SMTP/IMAP ✔ Real-time dashboard metrics integration with React frontends ✔ Event-driven architectures and scalable Node.js services Technical approach: • End-to-end chunk streaming pipeline for low-latency voice interactions • VAD-driven cancel/restart architecture for instant barge-in • Centralized event lifecycle management to eliminate memory leaks • Real-time metrics APIs/WebSockets for WhatsApp and Email dashboards • Draft approval workflow for AI-generated email responses Estimated timeline: 4–6 weeks depending on current codebase maturity. We would be happy to review the existing architecture and provide a detailed implementation roadmap. Best Regards, Karthik B Resonite Technologies

@Rajatt1099

Hi there, What outcome would make this engagement a success for you—the voice bot latency improvements, WhatsApp automation, or the complete omnichannel experience working seamlessly together? I've reviewed your requirements and can help optimize and stabilize your existing SaaS platform without disrupting the current architecture. My approach is to first audit the LiveKit voice pipeline, eliminate latency bottlenecks, implement reliable barge-in handling and stream interruption logic, then connect and optimize the WhatsApp and email campaign engines while exposing all metrics through your existing React dashboards. A little about me: I work on real-time communication systems, AI-powered automation platforms, Node.js backends, WebSocket architectures, telephony integrations, and LLM-driven workflows with a strong focus on performance and scalability. A few questions: 1. Is the current LiveKit deployment self-hosted or using LiveKit Cloud? 2. Approximately how many concurrent voice sessions and messaging campaigns must the platform support initially? 3. Do you already have production access to WhatsApp Business APIs and email infrastructure, or should setup and verification be included? I'd be happy to discuss the architecture, review the existing codebase, and outline the fastest path to production-ready performance. Feel free to send me a message via Freelancer.com chat so we can review the project and determine the best approach. With regards, Rajat Tiwedi

@Apponn

Hi, I went through your project and what stood out to me is that the frontend and core backend are already in place—you’re not looking for a complete rebuild, but for someone who can optimize and stabilize the existing system. I have experience working with Node.js, Express, WebSockets, AI integrations, and real-time applications. I understand the challenges around voice latency, interruption handling (barge-in), event listener leaks, and connecting WhatsApp/Email campaign metrics to existing dashboards. I’d be happy to review the current architecture, identify the bottlenecks causing delays, and help make the voice experience feel truly real-time while improving the reliability of the omnichannel workflows. Looking forward to discussing the details. Best regards, Rohit

@KarthikTechCon

Hello, I'm Karthik from Resonite Tech with 15+ years of experience in AI, Node.js, React, VoIP, and omnichannel automation platforms. I can optimize your existing LiveKit, Vobiz, and Sarvam AI ecosystem to achieve low-latency voice interactions, seamless barge-in handling, WhatsApp campaign automation, email workflows, and real-time analytics integration. ✔ LiveKit & Voice Pipeline Optimization ✔ Sarvam STT/TTS & Groq Integration ✔ Barge-In & Audio Buffer Management ✔ WhatsApp Business API Automation ✔ Bulk Email & Draft Approval Workflows ✔ Real-Time Dashboard Integration ✔ Memory Leak & Performance Optimization I can review your current architecture, identify bottlenecks, and deliver production-ready enhancements with clean documentation. Warm Regards, Karthik B Resonite Tech

@JorgeRAC

Developing an omnichannel automated outreach and inbound conversational SaaS platform is a complex task that requires expertise in multiple areas. I've built full-stack SaaS platforms and automated tools using Node.js and React, which could be useful in this project. As a new freelancer on this platform, I can offer a competitive rate and my undivided attention to deliver high-quality results and earn my first review. What specific challenges are you currently facing with integrating LiveKit and Vobiz into your platform?

@aaronrobs

⚡️Quality is Guaranteed⚡️ I can help you optimize your omnichannel SaaS platform with precision and expertise, ensuring ultra-low latency voice bot performance and seamless bulk messaging integration. ➡️ Core Deliverables - Optimize voice pipeline to eliminate delays using LiveKit and Vobiz SIP - Implement flawless barge-in and interruption logic with instant buffer flush - Fix memory leaks and event listener cleanup - Deploy WhatsApp Business API bulk campaign and analytics dashboard - Integrate bulk email outreach with AI-driven conversational flows and draft approval toggle - Connect backend metrics to your React frontend dashboards ➡️ My Approach - Analyze existing backend streams and perform surgical refactoring - Employ Node.js stream flushing and LiveKit turn-taking for real-time audio control - Use robust WebSocket and RTP event management for memory safety - Link omnichannel campaign data through efficient API endpoints - Provide clear documentation and production-ready code delivery Committed to delivering a high-quality product that meets your goals. I look forward to discussing this project further. Kind regards, Aaron Roberts

@goranm16

Hi, this is a strong fit for my work around real-time voice agents, automation, and omnichannel AI workflows. The main goal here is not rebuilding the SaaS, but making the existing backend behave reliably under live conversation pressure: lower voice latency, clean barge-in, and connected WhatsApp/email campaign flows. I’d start by tracing the current audio path end to end, especially where buffering, EventEmitter leaks, and stale listeners are causing delayed or replayed speech. Then I’d refactor the LiveKit/SIP/STT/LLM/TTS flow into proper chunk streaming with a clear cancel-and-restart path when the user speaks. For WhatsApp and email, I can connect campaign sending, reply triggers, draft approval, and dashboard metrics without disturbing the frontend. The main risk is breaking working real-time logic, so I’d make small backend changes, test each pipeline separately, and document what changed. I’m available 40 hrs/week at $15/hr. Thanks!

@alexbpo

Hi! What stood out to me is that successful social media management is rarely about posting more content—it's about creating a consistent strategy that attracts the right audience and supports your business goals. Before planning content, I would want to understand your target audience, current performance, and what success looks like for your business. Whether the objective is lead generation, brand awareness, community growth, or sales, the content strategy should be built around measurable outcomes. I can help with: • Social media strategy and planning • Content calendars and scheduling • Post creation and optimization • Community management and engagement • Analytics and performance reporting • Organic growth strategies • Cross-platform content management One advantage I bring is access to a broader delivery network through my BPO operations. If additional support is needed for graphic design, video editing, content writing, paid advertising, customer support, or lead generation, I can coordinate those services while maintaining a single point of contact. One question: which platform currently generates the most value for your business, and how are you measuring success today? Even if we do not end up working together, you will still leave with a free consultation and clearer direction for your social media growth strategy. Regards, Alex

@ApieTech

Fixing the 4–7 second LiveKit pipeline delay via end-to-end chunk streaming with Sarvam Saaras STT → Groq → Bulbul TTS is exactly the backend surgery we do. We've built real-time voice bot infrastructure on Node.js with WebSocket/RTP streams and VAD-based barge-in handling — including cancel-and-restart buffer flush logic. We've also integrated WhatsApp Business API bulk campaigns with webhook-driven inbound flows, and connected campaign analytics to React dashboards — so all three workstreams in your scope are familiar ground. Our approach: audit your existing EventEmitter leaks and pipeline config first, fix barge-in interruption, then wire WhatsApp + email metrics to your frontend. Clean, documented code throughout. Ping me and we can dig into your current STT-LLM-TTS latency breakdown — that'll sharpen the timeline.