You will get a custom voice AI agent with speech, tool calling, and memory
Project details
A voice assistant only feels good if it answers fast, understands accents, and does not talk over the user. Most demos fall apart when someone speaks naturally or asks it to do something real. Taking action is where a voice agent earns its keep.
I build custom voice AI agents that listen, think, speak back, and call your tools when the user needs something done. Speech in, an LLM brain (Claude or GPT), and natural speech out, in one clean pipeline.
What you get:
• A working voice agent: the user speaks, it transcribes, reasons, and replies out loud
• Tool and function calling so it can take real actions, not just chat
• Conversation memory so it keeps context across turns
• Latency tuning and a calm fallback for unclear speech, not a frozen mic
Where voice breaks: slow round trips, no handling for interruptions, no graceful path when transcription is wrong. I design for these from the start, because they separate a real voice agent from a demo.
For teams who want voice that does real work, on the web, in an app, or over the phone. Not sure which stack fits? Send a short note on your use case and I will tell you straight before you order.
I build custom voice AI agents that listen, think, speak back, and call your tools when the user needs something done. Speech in, an LLM brain (Claude or GPT), and natural speech out, in one clean pipeline.
What you get:
• A working voice agent: the user speaks, it transcribes, reasons, and replies out loud
• Tool and function calling so it can take real actions, not just chat
• Conversation memory so it keeps context across turns
• Latency tuning and a calm fallback for unclear speech, not a frozen mic
Where voice breaks: slow round trips, no handling for interruptions, no graceful path when transcription is wrong. I design for these from the start, because they separate a real voice agent from a demo.
For teams who want voice that does real work, on the web, in an app, or over the phone. Not sure which stack fits? Send a short note on your use case and I will tell you straight before you order.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
AI Text-to-Speech, Automatic Speech Recognition, Conversational AI, Natural Language Understanding, Speech SynthesisAI Development Language
PythonAI Models
ChatGPT, GPT-4, WhisperWhat's included
| Service Tiers |
Starter
$500
|
Standard
$1,500
|
Advanced
$3,500
|
|---|---|---|---|
| Delivery Time | 7 days | 14 days | 24 days |
Number of Revisions | 1 | 2 | 3 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | - | - |
Detailed Code Comments | - | - | - |
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | ||
Model Documentation | |||
Model Monitoring | - | - | |
Model Testing & Optimization | - | ||
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | - | - | - |
Source Code |
Frequently asked questions
1 review
(1)
(0)
(0)
(0)
(0)
This project doesn't have any reviews.
FO
Fatih O.
Jun 30, 2026
MCP Server Integration & Voice Assistant MVP Development (1-2 Week Sprint)
Working with Yu has been an absolute pleasure and an incredible journey. We just wrapped up a high-intensity, two-week sprint for a demo project, and the dedication Yu showed was unmatched. Yu is like a marathon runner—extremely fast, highly efficient, and was practically online whenever I logged in, completely shattering any timezone barriers. What I admired most was the obsession with the smallest details, which truly elevated our project to a remarkable level. Even though we only communicated via text, we built a fantastic rhythm and a strong bond of trust. If you are looking for a brilliant developer who genuinely cares about the craft and delivers flawless work under a clock, look no further. I will absolutely be opening a new contract with Yu very soon. Highly, highly recommended!
About Yu Fong
AI Voice Agent Developer | Vapi, Retell, ElevenLabs, Twilio, MCP
Taipei, Taiwan - 5:14 am local time
Today I run 12 conversational AI agents live in production: they listen, classify intent, answer what's in scope, and hand off to a human the moment they're out of their depth — with memory, dedup, anti-loop guards, and confidence-gated escalation so they don't hallucinate or spam. I've shipped omnichannel support inboxes end to end (Telegram, WhatsApp, Crisp), earned 5★ on my last delivery, and built a production voice assistant in a high-stakes domain (multi-LLM voice pipeline + MCP tool-calling).
Where voice and chat agents actually break isn't the model — it's the seams: latency, flaky function-calling, no clean human handoff, no state recovery after a restart. That's my lane. Stack: Vapi/Retell, Twilio, ElevenLabs/Deepgram, LLM function-calling, FastAPI webhooks, MCP, Python.
What I won't waste your time on: "AI strategy" decks, ChatGPT wrappers you could build yourself, or a demo that was never built to survive real customers. I quote, scope, ship, and hand off documented code with a runbook.
Taipei (GMT+8). Text-first, fluent written English, same-day replies.
Steps for completing your project
After purchasing the project, send requirements so Yu Fong can start the project.
Delivery time starts when Yu Fong receives requirements from you.
Yu Fong works on your project following the steps below.
Revisions may occur after the delivery date.
Scope the voice flow and stack
I map the conversation, then pick the speech-to-text, LLM, and text-to-speech that fit your latency and budget.
Build the voice pipeline
Speech in, an LLM brain, natural speech out, wired into one pipeline with tool calling.