Two languages, one sentence
Turkish suffixes stay correct on English stems: endpoint'i, GitHub'daki, API'ye. Meaning is never changed and your sentence is never rewritten; it is just spelled correctly.
Speak Turkish.
Keep the English words in English.
TrenVoice is a dictation app for iPhone with a companion keyboard, built for people who mix Turkish and English in one sentence. Say "production'daki endpoint'i deploy ettim" and that is exactly what appears on screen, not a phonetic guess at it.
Coming soon to the App Store
- No subscription
- No word limit
- No account
TrenVoiceListening
Staging'de çalışan build'i production'a deploy ettim ama cache yüzünden request'ler fail oluyor.
Runs locallyInsert
Turkish dictation spells English words the way it hears them
In code-switched speech the results are usually funny, and they always need cleaning up by hand. Developers, engineers and anyone working with a technical team live this daily. TrenVoice treats these sentences as ordinary use.
The result that drives you mad
The TrenVoice result
The result that drives you mad
The TrenVoice result
The result that drives you mad
The TrenVoice result
The result that drives you mad
The TrenVoice result
The result that drives you mad
The TrenVoice result
“prodakşın”
production
“stajyer”
staging
“diploy”
deploy
“keş”
cache
“gitab”
GitHub
“branş”
branch
“mayın”
main
“merç”
merge
“kumite”
commit
“ribeyz”
rebase
“doktor”
Docker
“klaudfleyr”
Cloudflare
“kıvırı”
query
“çıra”
Jira
“işi”
issue
“miting”
meeting
“dedlayn”
deadline
“fitbek”
feedback
“fol yap”
follow-up
“kola”
call
“forvet”
forward
“şer”
share
“pul rikuest”
pull request
“supabeys”
Supabase
“kreş”
crash
“tokat”
token
“bağ”
bug
“fok”
fork
“istek”
stack
“bordo”
board
“Leyla”
label
“reaktör”
refactor
“rol bek”
rollback
“bild”
build
“fiçır”
feature
“apdeyt”
update
Three design decisions
Audio never leaves the phone
The speech model is downloaded once; everything after that runs on device. It works in airplane mode. No audio, text or usage data is sent anywhere.
No quotas, no limits
No word quota, no monthly minutes, no per-dictation charge. Transcription runs on your own hardware, so there is no recurring cost behind it.
Record, review, insert
Three steps to voice typing. Nothing is typed anywhere until you say so.
Record
Start from the app, the Action Button or a Shortcut. You get an unambiguous "listening" indicator; while the model is still loading it says "preparing" instead.
Review
The raw transcript and the glossary-corrected version sit side by side. Any correction you dislike can be reverted individually.
Insert
Switch to the TrenVoice keyboard in WhatsApp, Teams or Mail and tap Insert. The text lands at your cursor. Nothing is auto-sent and no Return is simulated.
Why does recording start in the app?
iOS does not allow custom keyboards to access the microphone. That is Apple's platform rule, not our design choice. So recording happens in the app and the result is inserted from the keyboard with one tap. Nothing is ever pasted automatically. In places where iOS mandates the system keyboard (password fields, for example) this flow does not apply and the system keyboard takes over.
Apple's own documentation: custom keyboards have no access to the device microphone
- Microsoft Teams
- Slack
- Notes
- Telegram
Your own technical glossary
Add the terms you actually use and TrenVoice spells them the same way every time, with the right capitalisation and the right Turkish suffix. The glossary stays entirely under your control. You add to it, delete from it and edit it.
Corrections arrive as suggestions and can be reverted. A rule you have not approved is never applied. Numbers, negations, URLs, version strings and code-like tokens are never "corrected". No change that would alter the meaning of a sentence is made silently.
9:41
TrenVoice
A
- APIAPI'ye
B
- backlogbacklog'u
- branchbranch'ini
- briefbrief'i
C
- cachecache'i
- CloudflareCloudflare'e
- commitcommit'leri
D
- deadlinedeadline'ı
- deploydeploy'ladım
- DockerDocker'ı
E
- endpointendpoint'i
F
- feedbackfeedback'leri
- FigmaFigma'da
- follow-upfollow-up'ı
G
- GitHubGitHub'daki
H
- hotfixhotfix'i
J
- JiraJira'da
M
- meetingmeeting'den
- mergemerge'ledim
N
- NotionNotion'da
O
- onboardingonboarding'e
- OpenAIOpenAI'ın
P
- pnpmpnpm'i
- PostgreSQLPostgreSQL'de
- productionproduction'da
- pull requestpull request'i
Q
- queryquery'yi
R
- rebaserebase'ledim
- rollbackrollback'i
S
- sprintsprint'i
- stagingstaging'de
- SupabaseSupabase'teki
T
- TypeScriptTypeScript'te
W
- webhookwebhook'u
Search
What is collected, and what is not
How audio, text and usage data are handled on the device.
Audio never leaves the device
Your speech is held in memory only for the duration of the session and released when it ends. Keeping a recording is a separate, explicit action.
No account, no sign-in
No email, no phone number, no username. There is nothing to sign up for.
Offline after setup
Once the model is installed, the dictate, correct and insert path makes no network requests at all. It is tested in airplane mode.
History is off by default
If you do turn it on, transcripts stay on your device and can be deleted completely whenever you want.
The keyboard does not collect what you type
It records no keystroke history and makes no attempt to identify which app you are in.
No analytics SDK
No third-party trackers, no advertising identifiers, no behavioural telemetry.
The only network traffic is the initial speech-model download. During that download ordinary connection metadata such as your IP address is visible to the model host; no audio or text is sent. You can also install the model from your own local file instead.
TrenVoice, built-in iOS dictation and cloud services
The practical differences between on-device speech to text and cloud dictation services.
| Built-in iOS dictation | TrenVoice | Cloud dictation apps | |
|---|---|---|---|
| Turkish + English in one sentence | Limited | Primary design goal | Varies |
| Works offline | Device-dependent | Yes (after setup) | No |
| Audio sent to a server | Device-dependent | No | Yes |
| Account required | No | No | Usually yes |
| Monthly subscription | No | No | Usually yes |
| Word or minute quota | No | No | Common |
| Personal technical glossary | No | Yes | Sometimes |
Based on publicly available product information and our own daily use. Apple's on-device dictation behaviour varies by device, language and iOS version, and cloud services differ by provider.
Frequently asked questions
What is TrenVoice?
TrenVoice is a dictation app for iPhone with a companion keyboard, designed to correctly spell the English technical and everyday words that appear inside Turkish speech. It converts speech to text; it does not read text aloud, translate, or record meetings.
How does it get mixed Turkish-English sentences right?
Two layers work together inside TrenVoice: a multilingual speech model running on device, and your own approved glossary of terms. The glossary only touches terms you added and the Turkish suffixes attached to them; the rest of the sentence is left exactly as spoken.
Is my audio or text sent to a server?
No. TrenVoice dictation runs entirely on your device, and your audio and text are never sent to a server. The only network traffic is the initial speech-model download.
Does it work without internet?
Yes. TrenVoice works without an internet connection once the speech model is installed: recording, transcription, correction and insertion all run in airplane mode.
Can I dictate from inside the keyboard itself?
No, iOS does not permit custom keyboards to use the microphone. Recording in TrenVoice therefore starts in the app: from the app itself, the Action Button or a Shortcut. The result appears in the keyboard and lands at your cursor when you tap Insert.
Which apps does it work in?
The TrenVoice keyboard works in apps that accept custom keyboards: WhatsApp, Teams, Slack, Mail, Notes and similar. It does not work in fields where iOS mandates the system keyboard, such as password fields, or in apps that reject custom keyboards outright. We will publish the list of apps we have tested at launch.
Is there a subscription or a word limit?
No. Because TrenVoice runs recognition on your own device there is no word quota, no monthly cap and no per-use charge. Pricing will be announced closer to launch.
Which iPhones are supported?
TrenVoice runs on iPhones with iOS 26 or later. The on-device model needs meaningful compute and memory, so it performs noticeably better on recent iPhones. The exact supported list will be published at launch.
When is it launching?
There is no launch date for TrenVoice yet, and no App Store listing yet either. The app is currently being tested on physical devices while the speech model's Turkish-English performance is measured against our own test set.
Coming soon to the App Store
TrenVoice is being tested on physical devices right now. We will announce the date on this page.
iPhone · iOS 26+