NEXT_Storm is an offline-first dictation workspace built around the Neural Buffer Protocol:

NEXT is an offline-first dictation workspace built around the Neural Buffer Protocol: speak, capture into a buffer, review, optionally transform with AI, and only then insert the final text into the target window.
Links and contacts
Website: https://standaloneaistorm.com]
Repository: https://github.com/adamgold1/Storm_Mic
Support: support@standaloneaistorm.com
Sales: sales@standaloneaistorm.com
Enterprise: enterprise@standaloneaistorm.com
Languages: English | Русский | Español | 中文 | हिन्दी | العربية
English
What NEXT is
NEXT is a desktop application centered on the Neural Buffer Protocol:
Capture voice
Store text in a reviewable buffer
Edit or clean it up safely
Optionally use local AI tools
Insert the final result into the target app
Main public functionality
Dictation and Buffer workflow
Buffer-first dictation instead of immediate typing
Buffer Editor with manual correction before insertion
Insert to Window / fast insert workflow
Translation panel inside Buffer Editor
AI transforms for selected or full text
Save current text to buffer history
Buffer history with starred sessions
Open notes from the buffer
File-to-text workflow for local media and supported sources
Turbo Engine for background video transcription workflow
AI and Ollama
Local AI chat through Ollama
AI text transforms through Ollama
Model/provider/base URL configuration
Install / Check Ollama
Reload AI Model
Delete Unused Models
Local model management from the UI
Chat sessions stored separately from buffer history
Nexus Control Center
AI Core settings
Advanced settings
TTS Engine settings
System Audio settings
Speech Words / vocabulary settings
Platform dependency checks
Update check
Feedback sending
Nexus Notes workspace
Editor
Canvas
Organizer
Mind Map
Kanban
Drawing
Video
Studio
Audio
Sys Audio
File browser
Session/history panels
Starred sessions
Media, screenshots, and capture
Local video/audio transcription
YouTube processing if supporting tools are installed
Screenshot panel
Area capture
Window capture
Editor capture
Screen recording
Camera / media workflows
System audio capture and transcription
Speech engines and voices
Vosk
Smart Type
STORM STT
Whisper-based paths
Offline Piper TTS
Voice/model-related settings from UI
Main hotkeys
Ctrl + ~ — start/stop recording
Ctrl + Space — open/close Buffer Editor
Alt + Space — open/close Nexus Control Center
Ctrl + Alt — screenshot panel
Hold Space, then press Ctrl — open Nexus Notes
Double-tap Ctrl — fast insert
Ollama
AI chat and AI transforms require Ollama.
Official site: https://ollama.com
In app: 🛠️ Install / Check Ollama
After changing model/provider settings: 🔄 Reload AI Model
Privacy and storage
Dictation and local processing can run fully on your device
Ollama-based AI can stay local
Buffer history is stored locally
Chat history is stored locally in a separate database

Replies