Need an AI specialist: deployment of a fast local voice assistant (STT + Local LLM + TTS)
880 USDProject: Web Panel for AI Outbound Calling with Dynamic Agent Configuration
Core Concept: Develop a fully functional web application to manage outbound calls powered by an AI agent. The system is based on a local LLM (Llama, Deepseek, Gemma) and must feature a configuration panel to tailor the agent's behavior per call (voice, language, prompt), a lead management module, and detailed call analytics.
Key Quality Requirements: Low latency under 800ms and natural, human-like speech with appropriate pacing and pauses.
Core Modules:
1. Agent Configuration Panel (Web UI)
Allows users to select the following before a call:
- Languages: EN, DE, ES, NL (determines available voices and transcription accuracy)
- STT Model: Choose transcription engine (Deepgram / Cartesia / Gemini)
- TTS Provider & Model: Choose synthesis backend (Cartesia / Deepgram / ElevenLabs)
- Voice Selection: Select specific voice to define tone and style
- Silence Timeout: Set delay before re-prompting/call end (Default 30s)
- First Message Mode: Toggle between Bot Speaks First or Wait for User
- Background Noise: Add ambient sound (office, call center) for realism
- Prompt & Context: Field for custom LLM prompts (full conversation flow) - Support for uploading example dialogues for few-shot learning + export for learning/feeding model
2. Lead & Call Management (Web UI)
- Upload and delete contact lists (CSV or manual entry)
- Real-time call controls in browser: Start, Pause, Stop
- Automatic call recording linked to each lead
3. Reporting & Analytics
Per call data includes:
- AI-generated call summary
- Call duration
- Full audio recording
- Translated transcript (English translation of the conversation)
4. Integrations & Telephony
- WebRTC calling direct from browser
- Integration with external SIP trunks (IP&IP SIP BASED) and Asterisk
5. Technical Requirements
- End-to-end latency must be 800ms or less
- Telegram notifications for call start, end, and results delivery
- Server recommendation and setup guidance to meet performance targets
Tech Stack Preferred:
- Backend: Python (FastAPI / Django / Flask)
- Frontend: React, Vue, or core HTML/JS
- AI:
- Local LLM as the core reasoning engine (Llama, Deepseek, Gemma) – developer must select and optimize the most suitable model for speed and quality.
- Cloud APIs for low-latency STT/TTS (Deepgram, Cartesia, Gemini, ElevenLabs) to ensure performance.
Ideal Candidate:
An experienced full-stack developer with expertise in orchestrating complex voice pipelines and the ability to rightly choose the most optimal, fastest, and most cost-effective models for each component (STT, local LLM, TTS) based on specific use cases and requirements.
- Start: as soon as possible (ASAP)
- Fixed budget: $1000 (motivated budget increase possible) с фул сорсами
- Long-term Cooperation:
We are also considering candidates who would be available for paid ongoing support and future project enhancements after the initial MVP is delivered.
Please include in your proposal:
- Links or descriptions of similar past work (AI calling, voice bots)
Confirmation that you can independently choose and justify LLM + STT + TTS
Deadline by which you can provide a working pipeline with latency ≤ 800ms
communication languages: UA RU EN
*The LLM names listed are just examples from my experience. If you know better, faster, or cheaper solutions for this task, feel free to suggest them. We're looking for a motivated candidate for long-term collaboration with appropriate financial reward.
-
Бомба проект , складнощів мульйон .. Але 800 мс. затримки то мабуть дуже занадто -
11Лабс - затримка при синтезу не менше чим 200 мс. (по моїм тестам 1 сек)
СТТ - не менше 0.3 сек. причому не віспер - це точно .
ЛЛМ - 0.5 сек. плюс (невеличка моделька якась)
але зате - на цпу І 4-6 ЯДЕР НА один поток.
але ще ж якщо локальний ТТС- то живої мови не отримаете (можна але затримки зростуть в рази) -
нереальный проект, закройте пока вайбкодеры не пришли) вам же лучше будет, лапши навешают что все реально
-
ну - буде дуже цікаво побачити хочаб приблизний результат цього дійства
-
Current freelance projects in the category AI & Machine Learning
AI for processing order history and sending SMSAI for processing order history and sending SMS We have Quick Book online as our main accounting program. An automatic reminder system needs to be created to notify clients about upcoming orders. Data about orders needs to be imported from Quick Book online: Clients Invoices… AI & Machine Learning, Bot Development ∙ 1 hour 15 minutes back ∙ 11 proposals |
Technical consultant for hardware optimization and memory stability audit
1200 USD
Hello everyone! I am looking for a hardware specialist or systems engineer who can help me understand the unstable performance of my local server. I built it for work tasks, but it seems my amateur knowledge is not enough to get the most out of it. I would rather pay for an hour… AI & Machine Learning ∙ 4 hours 49 minutes back ∙ 3 proposals |
Marketing automation through AII'm looking for a person (not a bot) who understands AI agents and knows how to build them. By AI agent, I mean: processing input data, making a request to a 1x LLM or similar AI model, potentially requesting MCP or similar, potentially requesting a RAG system, processing output… AI & Machine Learning ∙ 6 hours 11 minutes back ∙ 17 proposals |
Creation of AI AgentAn AI agent is required to perform the functions of a professional packaging designer for a sports nutrition brand. The agent should assist in developing new product designs, creating labels, and adapting existing layouts for various markets and requirements.Main tasks of the AI… AI & Machine Learning, AI Art ∙ 6 hours 46 minutes back ∙ 18 proposals |
"Automation / Chatbots" "CRM Setup"
112 USD
Looking for a technical assistant/integrator to set up automation in a beauty salon. Setting up a chatbot for the beauty salon (Integration of Instagram + Altegio/YCLIENTS + Wahelp) with training. Current setup: CRM system: Altegio (YCLIENTS). Main traffic channel: Instagram… AI & Machine Learning, Bot Development ∙ 1 day 3 hours back ∙ 29 proposals |