Project News
Latest updates, features, and releases from SelenaCore.
SelenaCore Update: High-Speed Offline Voice Recognition with Vosk Migration
We have officially transitioned from Whisper to Vosk, introducing real-time streaming speech-to-text, advanced audio mixing, and a database-backed prompt management system.
SelenaCore Update: Personalizing Voice Intelligence and Dynamic Intent Management
We've upgraded SelenaCore with per-voice customization, a flexible database-driven intent system, and dual Piper TTS support for superior audio performance.
SelenaCore Update: High-Performance Voice Intelligence and Hardware-Accelerated STT
Significant upgrades to voice processing including NVIDIA Jetson GPU acceleration, AI-driven speech optimization, and a new real-time monitoring terminal.
SelenaCore Update: Introducing Auto-Learner and Multi-Tier Intent Intelligence
SelenaCore evolves with a new Auto-Learner module, multi-step AI classification, and a redesigned interface for managing system intelligence.
SelenaCore Update: Advanced TTS Queue Management and Intelligent Audio Ducking
New enhancements to the voice system introduce a sequential speech queue and audio ducking, alongside improved test environment isolation.
SelenaCore Update: New Prompts UI and Enhanced Multilingual Logic
We've introduced a dedicated Prompts tab for real-time editing and expanded multilingual support for intent classification across six languages.
SelenaCore Update: Introducing SmartHome SDK and Advanced Module Ecosystem
Launching the smarthome_sdk, expanding Zigbee support, and hardening API security through integrity-aware IPC and OAuth proxies.