constellation · 01
✦ mind
Mind.
How you think — reflection, openness, formality — traced across cognitive bands.
reflection0.91
openness0.76
formality0.30
your digital twin
·
42 seconds a day
Your voice builds
a Digital Twin
that knows you.
DailyVox is a free voice journal for iPhone with on-device AI. Speak for 42 seconds — or longer. The app transcribes your voice on-device and builds a Digital Twin, an AI model of your personality and inner world. It lives on your phone. It never leaves. It's yours.
0rpc
network
9
frameworks
∞
private
$0
forever
voice_entry.live · recording on-device
SFSpeechRecognizer → NLTagger → TwinEngine
sentiment
+0.00
entities
—
Twin
idle
network
0 B sent · local only
✦
how it works
Three steps. Forty-two seconds.
No typing. No prompts. No setup. Just speak — and your Twin takes shape.
01
Speak
Tap the mic and talk for 42 seconds. About your day, a feeling, a memory — whatever's on your mind. Your voice is transcribed on-device.
02
Your Twin learns
Every entry feeds your Digital Twin — a private model of your personality, emotions, and the people and topics in your life. It lives on your phone.
03
Patterns emerge
Over days and weeks, your Twin reveals mood trends, predicts emotional shifts, and answers questions about who you are. The longer you journal, the deeper it sees.
· · ✦ · ·
the vision
Your Digital Twin is the most accurate mirror of yourself that has ever existed.
It remembers everything you've shared. It sees patterns you can't. Over time, it learns how you think, how you feel, and who you mention. It predicts your mood before you journal. It answers questions about your personality. And it runs entirely on your phone — private, permanent, yours alone.
Knows how you think
Communication style, formality, reflection depth — measured across every entry.
Knows how you feel
Emotional patterns, mood baselines, triggers — tracked over time with sentiment analysis.
Knows your world
People, places, topics — a knowledge graph of everything that matters to you.
Predicts your tomorrow
Mood forecasting using temporal, linguistic, and topic patterns from your past entries.
Not a chatbot. Not a prompt tool. A private, evolving model of who you are.
meet your Twin
The constellations within your Twin.
Your Twin isn't one model — it's a constellation of dimensions. Mind for how you think, Voice for how you speak, Heart for how you feel, and a Graph of who and what you mention. In v1.4 a fifth dimension joins them — Body, layering sleep, HRV, and movement context underneath your words. Below it all, a forecast of where you're headed.
constellation · 02
✦ voice
Voice signature.
How you speak — rhythm, tone, pace — measured as a live acoustic fingerprint.
● warm
152 wpm
pauses · low
expressiveness0.68
directness0.55
live vitals
mind
0.91
voice
0.68
heart
+0.42
graph
42
body v1.4
at_rest
14:22:28 ✓ boot · on-device · 0 rpc
14:22:30 ▸ ingest entry #143 · 02:14 audio
14:22:31 ▸ twin.update · valence ▲ +0.04
14:22:33 ✓ persist AIState · 4.2 KB · local
constellation · 03
✦ heart
Emotional signature.
How you feel — valence, arousal, dominance — as a breathing field of colour.
valence+0.42
arousal+0.28
constellation · 04
✦ graph
Knowledge graph.
Who and what you mention — weighted by how you feel when you mention them.
entities42 nodes
top-mentionSarah ×18
constellation · 05
✦ body
◆ next · v1.4
Body signature.
How your body is — sleep last night, morning HRV, resting heart rate, and the activity context around each entry. Pulled from Apple Health on iPhone; sampled live during the recording on Apple Watch — but only when you're at rest, so a jog isn't mistaken for emotional stress. Every entry gets a body_context tag (at_rest / active / post_workout) so the Twin knows how to read it.
sleep 7h 12m
HRV 48 ms
HR Δ (recording) +4 bpm
context at_rest
steps today 6,420
mindful 12 min
on-device only · "Data Not Collected" privacy label preserved · Read the full Body Twin plan →
constellation · 05 · forecast
Tomorrow's mood.
tomorrow · +0.58 · leaning positive
TUE
+.58
WED
+.44
THU
+.38
FRI
+.62
SAT
+.74
SUN
+.68
MON
+.50
how it learns
From voice to Twin, five stages.
Every journal entry flows through the same on-device pipeline. Click any stage to see what happens to your data at each step. (Spoiler: nothing leaves the phone.)
stage 01 · capture
Microphone to raw audio, locally.
AVAudioEngine captures AAC audio at 44.1 kHz directly from the iPhone
microphone. The buffer is held in memory and handed to the transcriber —
never uploaded, never cached to disk.
- framework
- AVFoundation
- format
- AAC · 44.1 kHz
- latency
- < 10 ms
- network
- 0 rpc
live view
✦ · · ✦ · · ✦
your data shield
Nothing. On purpose.
Attach a network proxy during a 2-minute voice entry. Run the transcription, NLP, and Twin update. Zero bytes leave the device. This isn't a promise — it's the architecture.
0rpc
network calls
Every AI operation runs on Apple's Neural Engine. Zero outbound requests.
0sdk
third-party
No analytics, crash reporting, or ad SDKs. Apple frameworks only.
AES-256
encryption
GCM authenticated encryption for backups. Keys in the Secure Enclave.
—
account required
Data Not Collected — Apple's strictest privacy label.
✦ your constellation is shielded ✦
why voice
Typing filters. Speaking doesn't.
When you type, you edit. When you speak, you think out loud. Voice journaling captures more of who you actually are — unfiltered, unpolished, real.
3.8×
faster than typing
Speaking at 150 WPM vs typing at 40. More thoughts captured in less time.
0
blank page anxiety
No cursor. No blinking prompt. Just press record and start talking.
42sec
is all it takes
The answer to life, the universe, and everything — and enough for a meaningful entry.
the stack
Nine Apple frameworks. Zero vendors.
DailyVox is built entirely on Apple's on-device SDKs — no third-party dependencies anywhere in the app. Every capability has a home inside iOS.
Sp
SFSpeechRecognizer
Speech.framework
On-device transcription with requiresOnDeviceRecognition = true. 60+ languages on the Neural Engine.
Nl
NLTagger
NaturalLanguage
Sentiment scoring, Named Entity Recognition, part-of-speech, and language identification — four CoreML models running locally.
Ne
NLEmbedding
512-dim vectors
Dense sentence embeddings for semantic search and k-means thematic clustering of your journal.
Fm
Foundation Models
3B on-device LLM
LanguageModelSession with tool calling, @Generable structured outputs, streaming.
Sa
SpeechAnalyzer
next-gen ASR
Replaces SFSpeechRecognizer in v1.6. Lower latency, native long-form support, no permission prompts.
Cd
Core Data + CloudKit
NSPersistentCloudKitContainer
Local SQLite with optional end-to-end-encrypted sync. The Twin is one AIState Codable JSON entity.
Ck
CryptoKit
AES-256-GCM
Authenticated encryption for backup exports. Passphrase-derived keys for device migration.
La
LocalAuthentication
Face ID · Touch ID
Biometric gating on every journal access. Keys stored in the Secure Enclave — never extracted.
Wk
WidgetKit + AppIntents
widgets · siri
Home & Lock-screen widgets. AppIntents-powered Siri shortcuts for hands-free entries.
next to the category
How it compares.
| DailyVox | Day One | Reflectly | Apple Journal | Calmplot | |
|---|---|---|---|---|---|
| price | free forever | $34.99/yr | $59.99/yr | free | $5.99/mo |
| voice journaling | ✓ | — | — | — | ✓ |
| on-device AI | ✓ | — | — | partial | — |
| Twin · chat + predictions | ✓ | — | — | — | — |
| works offline | ✓ | partial | — | ✓ | — |
| data collected | none | yes | yes | minimal | minimal |
| account required | no | yes | yes | no | yes |
| open source | ✓ | — | — | — | — |
shipped in v1.1 & v1.2
Your Twin already does this.
Features that shipped since launch — your Twin predicts, converses, and shares.
Tp
Twin Predictions
mood forecasting
Your Twin anticipates mood shifts, identifies emotional triggers, and detects temporal patterns — day-of-week, seasonal, and trend-based.
At
Ask Your Twin
conversational chat
Have a conversation with your Digital Twin. Ask it questions about your patterns, moods, and personality — entirely on-device.
Sc
Shareable Cards
personality cards
Share your Twin's personality snapshot as beautiful cards — optimized for Instagram Stories and Twitter/X.
what's next
Where the Twin is going.
Every feature below runs on-device. No cloud. No compromise.
Bt
Body Twin · HealthKit + Apple Watch
v1.4 · the Twin gains a body
Sleep, HRV, resting heart rate, and activity context feed the Twin. Apple Watch records from your wrist and samples heart rate during entries — only when at rest. Context-aware so a jog isn't mistaken for stress.
Se
Semantic Search
v1.5 · NLEmbedding
Find entries by meaning, not keywords. 512-dimensional embeddings, K-means clustering, and anomaly detection surface hidden patterns. Foundation for on-device RAG.
Fm
Conversational Twin
v1.6 · Foundation Models
A 3B on-device LLM powers deep conversations with your Twin, with answers that cite your own entries. Then v2.0 goes Apple Intelligence native: ask Siri and it consults your Twin — context flows in, nothing flows out.
Ds
True Digital Self
v3.0 · the vision
After years of entries: a Twin that talks like you, sounds like you, and knows how you've changed. Not a clone — a mirror that deepens every day.
common questions
The honest answers.
Is it really free?
Yes. Every feature, forever. No paywall, no premium tier, no "free trial." DailyVox is free and open-source.
Do I need to create an account?
No. No signup, no email, no password. Install and start talking. Your data lives on your device, not on our servers — because we don't have servers.
What happens to my voice recordings?
They're transcribed by Apple's speech engine, on your phone. The audio is stored locally. Nothing is uploaded, ever. Run a network proxy during a recording and see for yourself — zero bytes leave the device.
How is this different from Day One or Apple Journal?
DailyVox is voice-first with an on-device AI that builds a Digital Twin of your personality. Day One is cloud-based and text-focused. Apple Journal has no AI. Neither has a Twin that learns who you are.
What if I miss a day?
Nothing happens. No streaks broken, no guilt trips. Your Twin is patient — it picks up right where you left off.
Can I export my data?
Yes. PDF, JSON, Markdown, CSV, or AES-256 encrypted backups. Your data is yours — always portable, never locked in.
· ✦ ·
note from the builder
“I wrote a diary for twenty years. Then I couldn't anymore. So I stopped writing — and started talking. That's how DailyVox was born, and why it runs entirely on your phone instead of someone else's server.”
Every voice-journaling app I could find shipped audio to a cloud for transcription. I didn't want my most private thoughts processed by a third party, and I didn't want to pay a subscription for it either. So I built my own — free, open-source, fully on-device. The Digital Twin is the next step: a model of you that lives on your phone, not on somebody's server. Read the full story →
from the journal
Writing about the work.
2026.04.01 · technical
How your Twin learns your personality.
Inside the TwinEngine — how NLTagger signals become a multi-dimensional personality model, on-device.
read →
2026.04.01 · privacy
Why your AI journal should work offline.
If the app needs the cloud to transcribe, it isn't private. The on-device test — and how to run it yourself.
read →
2026.04.01 · protocol
The ADHD voice-journaling protocol.
Speaking at 150 WPM versus typing at 40. A protocol for brains that think faster than their fingers.
read →
install · $0 · no account
Start talking.
Your Twin is waiting to be born.
Forty-two seconds a day. Your voice becomes a Digital Twin — a private AI that knows how you think, how you feel, and who matters to you. Free forever. No data ever leaves your phone.
Download free on the App Store →