https://seasalt.ai/ja/seavoice/ One of the projects I worked on is an AI voice agent platform called SeaVoice. The goal of this system is to automate business phone calls using conversational AI, replacing traditional IVR systems with natural voice interactions. From a technical perspective, the system is built as a real-time conversational pipeline. When a user calls the system, the audio stream first goes through a streaming Automatic Speech Recognition (ASR) service that converts the caller’s speech into text. That transcript is then processed by a conversational AI layer powered by a large language model. To improve response accuracy and reduce hallucinations, we implemented a Retrieval-Augmented Generation architecture. The system retrieves relevant information from a vector-based knowledge base and injects that context into the LLM prompt before generating a response. This allows the AI agent to provide accurate answers related to company services, FAQs, or product data. Once the response is generated, it is passed to a neural Text-to-Speech engine, which converts the text back into natural-sounding audio that is streamed to the caller. The system also includes a dialogue management layer that maintains conversation state so the AI can handle multi-turn interactions and follow-up questions. One of the biggest challenges we faced was reducing latency in the voice interaction pipeline, since ASR processing, LLM inference, and TTS generation can introduce delays. To address this, we implemented streaming transcription, asynchronous model inference, and incremental TTS playback so the system could start responding before the full pipeline finished. Overall, this project involved integrating multiple AI components—including speech recognition, large language models, vector search, and neural speech synthesis—into a scalable architecture capable of supporting real-time voice conversations.

I’m tired of seeing talented entrepreneurs waste hours on paperwork after their sales calls. It’s time to go on the offensive. I am looking for 3 businesses or agency owners who want to automate their proposal process from 45 minutes down to 10 seconds. What you’ll get: My ready-to-use n8n workflow (JSON file). A 1-on-1 implementation session (max. 30 min) to get everything up and running on your end. Full automation: End the call -> Generate proposal -> Done. Why am I doing this for free? I’m currently building the portfolio for my automation agency. I don’t want $500 right now; I want 3 rock-solid case studies and an honest video testimonial once it’s working for you. First come, first served. If you’re ready to scale your business and done with manual PDFs: 👉 Comment "SALES" below or send me a DM.

Started the free trial, imported the Json ChatGPT created for the workflow, initially would not work. Pasted the Json into the n8n chat.. boom! n8n created the workflow. Now one of the nodes needs the correct API. How am I doing?

Hi everyone 👋 I am an **AI and full-stack engineer** working on LLM systems, AI agents, automation, and multimodal AI (text, voice, and vision). Most of my work focuses on building AI systems that run in real production environments, not just demos. I usually connect LLMs with APIs, databases, tools, and business logic so they can operate reliably inside real workflows. **AI / ML Systems** > • LLM orchestration pipelines > • tool use (ReAct-style) and reasoning loops > • safety guardrails and grounded generation > • evaluation and reliability pipelines > • multi-agent workflows and memory systems > • RAG systems (vector databases, hybrid search, custom retrievers) > • document intelligence (PDF extraction, OCR, structured data pipelines) > • multimodal AI (text, voice, vision, audio pipelines) **Full-Stack & Infrastructure** > • React / Next.js frontends > • FastAPI / NestJS backend systems > • secure APIs and RBAC design > • automation pipelines (n8n, Zapier, Make, webhooks) > • API integrations and workflow orchestration > • cloud deployment and scalable backend systems > • monitoring, observability, and production reliability Recently I have also been exploring AI systems in the music industry, including music understanding, audio analysis, recommendation systems, and AI-assisted production workflows. I have worked on systems in areas like healthcare AI, document intelligence, and automation platforms. Always happy to connect with other builders, discuss architectures, or share experiments. Let’s build useful things together 🤝

Hello Everyone, I'd appreciate it if you look into my newly made portfolio and give me your honest feedback and what i can update. Link : farukportfolio.live Thank you again !