
Talking Avatar
A live face for the voice agent you already run.

What it does
Talking Avatar, from InterviewFlowAI, puts a face on a voice agent. The hosted Realistic Avatars stream a photorealistic person from your agent’s audio over WebRTC or LiveKit. A no-code Voice Agents setup adds the model, speech recognition, and a voice, then shares a link. A separate MIT-licensed 3D avatar runs in the browser with no server. The homepage shows a live demo and a library of ready faces.
Where it fits
Talk to the homepage demo before you create a key. Use the open-source 3D avatar if you do not need a photorealistic stream. Read the consent note before you order a custom face.
Before you commit
The homepage lists Realistic Avatars at $0.02 a minute, billed per second, and no-code Voice Agents at $0.06 a minute with the model and voice included. New accounts get $1 of free credits, described as 50 minutes. A custom avatar is $199 once, and sessions with it stay at $0.02 a minute. The open-source 3D avatar is free under MIT. This check did not start a paid session.
Release & update notes
Dates below refer to the linked announcement or Product Hunt launch. They are separate from the date this profile was added.
- Product Hunt launch · ↗
Product Hunt listed Talking Avatar on 4 November 2026.
Sources & editorial notes
This profile summarizes public product information and adds workflow guidance. It is not a hands-on performance review. Check the official website for current prices, limits, and availability.
- Official product website
- Product Hunt discovery
- Official homepage: realistic avatars at $0.02 a minute, no-code voice agents at $0.06 a minute, $1 of free credits, and a free MIT 3D avatar.
- Product Hunt launch by InterviewFlowAI: real-time lip-sync for a voice agent, plus the open-source browser SDK.
Source check:


