Perso Interactive NEW

Perso Interactive (ESTsoft) is an AI conversational interface that delivers real-time AI human interactions across PC, mobile, web, and kiosk environments.It combines conversational AI, vision-language understanding, and on-device gesture and facial-expression rendering to enable multimodal interaction with speech, visuals, and gestures.

Key features include multilingual real-time conversation (100+ languages), customizable AI avatars, TTS and custom voice modeling, STV (speech-to-video) lip-sync, and automated video dubbing for localization.

Perso AI Dubbing supports audio translation, voice cloning, and precise lip-sync across 32+ languages for video localization and marketing content.Perso AI Studio provides template-based 4K video creation from slides or documents, plus access to 6000+ multilingual voices for rapid content production without filming crews.

The Perso Interactive SDK integrates LLM APIs (e.g., GPT-3.5, HyperCLOVA X) and the Alan multi-agent LLM for enterprise search, workflow automation, and multilingual knowledge exploration.Typical use cases include airport and hotel kiosks, exhibition interactive stations, digital concierges, customer service automation, e-learning localization, and event engagement.

Benefits for enterprises and creators include scalable multilingual communication, automated video localization, reduced staffing for repetitive inquiries, and consistent cross-channel user experiences.

Key Features

• Real-time conversational AI Human with multilingual speech and interpretation (supports 100+ languages)
• STV (Speech-to-Video) engine: speech+video processing with face detection, landmark detection, segmentation, 3D-alignment and precise lip-sync
• Custom TTS and voice cloning with voice modeling, IP customization, multi-speaker support and a large catalog of multilingual voices
• AI Avatar / Face Creation for generating and customizing AI personas with natural gestures, facial expressions and appearance control
• Multi-LLM agentic architecture and integration (Alan LLM) plus Perso Interactive SDK and LLM model APIs (e.g., OpenAI GPT-3.5, HyperCLOVA X)

Use Cases

• Create multilingual, interactive customer service kiosks with Perso Interactive using customizable AI avatars, real-time speech, vision and gesture interactions, and precise lip-synced TTS/voice cloning for seamless in-person support across retail, airports, and events
• Produce localized 4K marketing and training videos fast by leveraging Perso Interactive's template-based video creation, automated video dubbing and voice cloning to generate accurate, lip-synced translations and consistent brand avatars without manual editing
• Integrate Perso Interactive's SDK and LLMs into web and mobile apps to build multimodal conversational assistants that handle speech-to-text, real-time translation, vision inputs and personalized dialogue for sales, onboarding, and accessibility

Who is it for?

• Software developers
• Content creators
• Business managers
• Educational educators
• Customer service providers