Browse categories
Explore
Fiverr Pro
English
$
USD
Our agency will develop video calling agents, voice calling ai, interactiv ai avatar, livekit
Trixly
Level 1
Agency
About this gig
I will develop video calling agents, voice calling ai, and interactive ai avatar solutions using LiveKit, Mediasoup, Zoom, or Google Meet. I build real-time communication platforms where AI doesn't just join calls it speaks, listens, reacts with avatars, and autonomously manages conversations.
What You Get:
- Video calling agents with AI participants that join, speak, and respond in real time
- Voice calling ai with natural speech synthesis, interruption handling, and emotion detection
- AI avatar with lip-sync, facial expressions, and real-time rendering in video calls
- LiveKit or Mediasoup infrastructure for scalable WebRTC streaming
- Zoom and Google Meet SDK integration for AI agent participation
- STT/TTS pipelines with Whisper, ElevenLabs, or Play.ht voice models
- Conversation memory, context awareness, and autonomous task execution
Tech Stack: LiveKit · Mediasoup · WebRTC · OpenAI · Whisper · ElevenLabs · Unity · Unreal Engine · Three.js · Node.js · Python
Ready to put AI in your calls? Message me your use case. I
About this agency
Trixly
Agency
3 employees
Level 1
- FromPakistan
- Member sinceAug 2023
- Avg. response time1 hour
- Last delivery1 week
Languages
Urdu, English
Trixly AI Solutions engineers secure, human-guided systems that proactively identify and execute on the highest-impact AI opportunities. We transform today's operational data into tomorrow's strategic supremacy by building Agentic AI ecosystems designed for sustainable business advantage.
By implementing a refined approach that keeps humans in the lead, we ensure that technology doesn't just automate tasks it amplifies human potential.
Portfolio
Other Software Development Services we Offer
FAQ
What are video calling agents and how do they work?
Video calling agents are AI participants that join video conferences through LiveKit, Mediasoup, Zoom, or Google Meet. They see and hear participants via WebRTC streams, process speech through STT, generate responses with LLMs, and speak back using TTS.
Can your voice calling ai sound natural and handle interruptions?
Yes. My voice calling ai uses advanced TTS models from ElevenLabs or Play.ht with low latency streaming. I implement barge-in detection so users can interrupt the AI naturally. The system also adjusts tone, speed, and emotion based on conversation context, creating human-like voice calling ai experi
What is an AI avatar and how does it appear in video calls?
An AI avatar is a real-time animated character that represents the AI in video calls. It lip-syncs to generated speech, shows facial expressions matching tone, and maintains eye contact with the camera.
