Questions &
Answers.

Still With You is an AI system that preserves a loved one's voice, memories, and personality so family members can continue having natural conversations with them. It runs entirely on a local device in your home -- no cloud, no subscriptions, no data collection. Think of it as a bridge between love and technology: their voice, their stories, their humor, available whenever your family needs them.

For any family that wants to preserve the presence of someone they love. Parents who want to leave something meaningful for their children. Families who have already lost someone and wish they could hear their voice again. Grandparents who want their grandchildren to know them. Anyone who understands that some voices are too important to lose.

Both. If you are planning ahead, you can record voice samples, enter memories, and prepare milestone messages for the future. If you have already lost someone, you can still build their presence from existing recordings (phone calls, voicemails, home videos) and family memories. The voice cloning works with any clear audio of their voice, and memories can be entered by anyone who knew them.

Fundamentally different in five ways. First, it runs 100% locally on your device -- no data ever touches a server. Second, it speaks with their actual cloned voice, not a generic AI voice. Third, it has a persistent memory system with 20 distinct types that remembers family stories, relationships, preferences, and personality traits. Fourth, it recognizes family members by face and by voice, and adjusts how it communicates based on who it is talking to and how old they are. Fifth, it includes a self-healing admin dashboard with encryption, hardware monitoring, parental alerts, and session history. It is not a chatbot. It is a preserved presence.

You provide 30 minutes of natural speech recordings -- not scripted readings, just them talking normally. The system extracts reference clips and learns their unique cadence, inflection, and emotional tone. When the system speaks, it synthesizes new speech in their voice in real time, preserving the warmth and personality of how they actually sounded.

About 30 minutes of natural speech. This does not need to be a single continuous recording. Multiple shorter recordings work well -- conversations, stories, even voicemails. The key is variety: different emotions, different topics, different energy levels. The more natural and varied the recordings, the better the voice clone captures their full range.

The voice will be recognizably theirs -- the cadence, the warmth, the way they pause before something important. Family members consistently recognize the voice as belonging to their loved one. Quality depends heavily on the input recordings. 30+ minutes of clear, natural speech produces a voice that family members will recognize. Poor-quality recordings (heavy noise, music, multiple speakers) will produce lower-quality results. We include preprocessing tools to improve audio, but we cannot produce studio-quality output from poor-quality source material. For most families with decent recordings, the first time they hear it, they know immediately who it is.

You can add additional reference clips to the voice folder at any time, and the system will use them for synthesis. Automated full voice retraining (re-processing all recordings to improve the model) is on our roadmap but not yet available in the current release.

If you have any audio at all -- phone voicemails, home videos, video calls, even social media videos -- the system can work with it. The audio does not need to be studio quality. If you truly have no recordings, the system can still function as a text-based presence with their memories, personality, and knowledge. Voice can be added later if recordings are found.

No. Zero data leaves your device. Every component -- voice synthesis, language model, memory database, facial recognition -- runs locally on the hardware in your home. There are no cloud servers, no API calls, no telemetry, no analytics. The device does not even need an internet connection to function. Your family's conversations are physically incapable of being transmitted anywhere.

No. We have no mechanism to access your data even if we wanted to. There are no remote access tools, no backdoors, no phone-home features. The software runs entirely on your device. We do not operate servers that store or process customer data. Your system is self-contained and we have no connection to it after delivery.

Nothing changes for you. Your device continues working exactly as it does today. All software runs locally. There are no license servers to check, no activation keys that expire, no cloud dependencies. The underlying AI technologies are open source and independently maintained by large communities. Your device is yours, permanently.

AES-256-GCM encryption can be enabled through the admin dashboard to protect your stored memories, conversation history, and personality profiles at rest on the device. PBKDF2 key derivation prevents brute force. You can bulk-encrypt or decrypt existing data at any time through the admin dashboard.

The device has no open ports to the internet and does not need a network connection to operate. This eliminates the most common attack vectors. For local network security, the web interface runs on your home network only. Facial recognition with IR liveness detection prevents spoofing with photos or screens. The attack surface is intentionally minimal because the device was designed to be offline-first.

All tiers are software-based -- you provide the hardware. The system requires an NVIDIA GPU with 24GB+ VRAM (RTX 3090 or newer) and runs on any Debian-based Linux PC -- a dedicated mini PC with GPU dock is one popular option (e.g. AtomMan X7 Ti + OCuLink dock), but any desktop with the right GPU works. You'll also need 32GB RAM, 512GB SSD, a USB webcam, and an external speaker. The Blueprint tier includes a verified hardware list with exact models and purchase links, plus a video build guide and setup call.

GPU: NVIDIA with 24GB+ VRAM, RTX 3090 or newer (required for full AI stack). RAM: 32GB recommended. Storage: 512GB SSD. OS: Ubuntu 22.04+ or Debian-based Linux. Camera: any USB webcam (IR-capable recommended for anti-spoofing). Speaker: external speaker or monitor with built-in audio. The GPU is the most important component -- it handles voice synthesis, language processing, and speech recognition simultaneously.

All tiers include a USB drive with all AI models pre-loaded. Plug it in, run the installer (~30 minutes), no internet required. The setup wizard walks you through the rest. Personal setup (voice recording, memory entry, facial enrollment) takes 1-2 hours. Blueprint and Legacy tiers include a 45-minute setup call. Legacy tier includes lifetime phone and FaceTime support.

No. The device works completely offline. You may want internet for initial software updates after unboxing, but once set up, the device never needs to connect to the internet again. All AI models, voice synthesis, memory storage, and facial recognition run locally on the device's GPU.

You are running the same AI models that big companies run in data centers -- but in your living room. Voice cloning, speech recognition, a conversational AI, and facial recognition all need GPU memory and they all run simultaneously. 24GB of VRAM is the minimum to run all of these at the same time with acceptable response times. The hardware cost is what you would otherwise pay in monthly cloud subscriptions -- except you pay once and own it forever. This is the real cost of privacy: the power to keep everything local.

Yes. The system was built by a father for his own children. It includes a four-level parental alert system that monitors conversations for sensitive topics — from critical issues like self-harm and abuse, to high-priority concerns like bullying and school threats, to medium topics like anxiety and peer pressure, plus positive info alerts for achievements and friendships. All alerts blink at speeds matching their urgency. For crisis situations like self-harm, the AI is bypassed entirely and a pre-written, loving parental response is delivered instantly. All content is age-appropriate and adapts to each child's developmental stage. Beyond alerts, the system enforces relationship-based privacy access — each person's enrollment relationship determines what memories they can see. Children's access expands gradually with age: academic content at 13, health information at 16, relationship matters at 18. Intimate content between parents stays private forever, regardless of the child's age.

Two ways: facial recognition and voice identification. Each family member enrolls their face during setup via webcam capture or by uploading existing photos -- no one needs to be present. The wizard collects 10 photos per person. Voice enrollment adds a second layer -- a few short voice clips teach the system to recognize each person by their voice alone. After enrollment, the system instantly recognizes who walks up and adjusts its personality, memories, and communication style accordingly. Both systems improve automatically over time by collecting samples during natural conversation. IR liveness detection prevents spoofing with photos or screens. No passwords or wake words needed.

A monitoring system that watches conversations with children for concerning content across four priority levels — all with visual blinking indicators scaled by urgency. Critical (red, fast blink): self-harm, abuse, running away. High (orange): bullying, school threats, stranger danger, weapons, fear of a person. Medium (blue): depression, anxiety, substance exposure, peer pressure, body image. Info (green): achievements, new friendships, crushes, kind behavior. Alerts are displayed when the parent is identified by facial recognition. Critical alerts trigger an immediate pre-written crisis response before any AI involvement. The system also includes relationship-based privacy controls: a spouse sees everything, extended family (parents, siblings) sees family content but not intimate details, and friends see only public memories. Privacy is detected automatically from memory content — no manual tagging needed.

Yes, if Math and Coding tutoring are enabled during setup. When active, the system automatically detects homework questions and switches to a dedicated math or coding AI -- handling everything from basic arithmetic to calculus, and programming across multiple languages. Both modes guide the child toward the answer rather than solving it for them, the way a patient parent would. Smart continuation detection keeps the session flowing naturally, and children can pick up where they left off the next day.

Yes. The system remembers every story it has told. If a child says 'Tell me that race car story again!' the system retrieves it and tells it again. Math and coding tutoring sessions are also remembered -- children can say 'Remember that trigonometry problem from yesterday?' and continue where they left off.

Yes. The Personalization Dashboard lets you fine-tune the preserved person's personality with simple sliders -- humor, warmth, sarcasm, playfulness, empathy, bluntness, and more. You can set different profiles for each family member: warmer and gentler with young children, wittier and more direct with a spouse. This is separate from the automatic age-adaptive system, which adjusts vocabulary and complexity based on a child's current age. Both work together.

The system includes an emotion tracking layer that observes emotional patterns in conversations over time. It does not diagnose or interpret -- it provides gentle awareness of how each family member is doing emotionally. This also helps the system respond with appropriate sensitivity. For the surviving parent, the admin dashboard provides conversation statistics per family member.

Yes. A 26-card admin dashboard gives you complete visibility: response times, GPU temperature and VRAM, disk SMART status and wear level, conversation statistics per family member, voice ID management, encryption status, session history, pattern learning rates, and more. The layout is draggable and customizable. The system also monitors itself -- watchdog services detect performance issues and auto-recover. When something gets sluggish, the system tells your family 'Let me stretch my brain...' and fixes itself. The dashboard is protected by an admin PIN.

The system respects children's privacy for non-safety matters like crushes, friendships, and achievements. But it always alerts on safety concerns -- self-harm, abuse, bullying, stranger danger -- regardless of confidentiality requests. The parent sees a gentle warning: 'Your child asked to keep this private. Be thoughtful in how you approach this.' This balances a child's need for a safe space with a parent's need to know when something is seriously wrong.

The system includes graceful degradation. If the GPU overheats, it automatically switches to a lighter model and warns the user. If the GPU becomes completely unavailable, a CPU fallback keeps conversations going at reduced speed. When the GPU recovers, the system switches back to full power automatically. Hardware health monitoring tracks temperature, VRAM, fan speed, power draw, throttle state, and disk wear -- all visible in the admin dashboard.

Yes. Conversations are naturally warmer and gentler at bedtime, briefer in the morning, and more playful in the evening. Family members can also adjust personality in conversation -- 'more humor,' 'be less sarcastic,' 'set warmth to 80' -- with immediate effect. No need to open the admin dashboard.

The system ships in English. Preliminary localization work has been done for Romanian and Greek, but these are not yet fully supported. Multi-language support for additional languages is planned via stretch goals.

During math and coding sessions, a lightweight remote view is available from any phone or tablet on the same home network -- useful for copy/pasting a complete math problem or a code snippet. Just open a browser on any device connected to the same WiFi. Remote access is only available for the duration of an active specialized mode session, not as a permanent connection.

All tiers are estimated for October 2026. Because every tier is software-based (no hardware sourcing or assembly), there is a single delivery window. Physical items (voice prompt cards, USB installer) have short manufacturing lead times. We will provide monthly updates throughout the fulfillment process.

Refunds follow the standard refund policy of the platform you backed on (Kickstarter or Indiegogo). Before the campaign ends, you can cancel your pledge at any time. After the campaign ends, refunds are handled on a case-by-case basis. We are committed to delivering on every promise and will work with backers to resolve any concerns.

Yes. The Seed tier is fully digital. The Voice, Blueprint, and Legacy tiers include lightweight physical items (voice prompt cards, USB installer) shipped via USPS. Shipping is free in the US; international shipping is $10-18 depending on region.