Skip to content

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

feat(notes): open notes on AI Summary, rename Notes tab to Your notes, 1.10.1 release prep (#2196)

Gabriel Stein7935da520693
diff --git a/CHANGELOG.md b/CHANGELOG.md
index a7a33f982..144a669e6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,16 +7,43 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
-### Dictation
+## [1.10.1] - 2026-09-14
-- **Windows pins the real microphone again.** Chromium lists the Windows default input twice, once as `default` and once as the `communications` alias, both with the device's own label. The selection code required exactly one label match, saw two, and fell back to Chromium's generic default, which it never caches, so every hotkey press re-resolved the device. Aliases are now ignored when matching, and the device is resolved once when the dictation window loads instead of on the first press. (#2180, thanks @Chadpiha)
-- **Dictation starts listening sooner on Windows.** Pressing the hotkey could take two seconds before the microphone opened. Since 1.9.0 the app pins the system-default microphone to a real device so its health checks can run, and on Windows finding that device means starting a PowerShell process that compiles C# on the fly — a lookup that ran on the first dictation after launch and again whenever an audio device came or went, and expired after 30 seconds either way. The answer is now resolved once at launch, kept until the OS reports a device change, and shared between windows, so the hotkey path only has to open the microphone. (#2178)
-- **Learned corrections skip everyday words.** When you fixed a transcript by swapping one common word for another, such as "why" for "what", the app treated the replacement as a mishearing and saved it to your dictionary. Those entries taught the cleanup model nothing and padded every request. Corrections that resolve to a common English word are no longer learned; names and jargon are unaffected. (#2178)
+A follow-up to 1.10.0 built from everything that landed since. Notes open straight onto their AI Summary when one exists and the raw tab becomes **Your notes**; the "Enhanced" label is gone in favour of **AI Summary** everywhere, a meeting that ends on its own still offers the summary, and the post-meeting notification is retired. Team spaces get one **Settings** dialog with a built-in emoji picker, the sidebar gains **Invite your team**, and the tray and dictation pill pick up quick actions. Uploads accept video and nearly every audio container, Windows finds the right microphone again and starts listening sooner, local dictation skips a decode step, and bring-your-own-key Deepgram and AssemblyAI work again. Cleanup no longer pastes a reply the model cut short, whisper.cpp stops dropping words at window boundaries, local models size their context to the request, and Reset app data restarts the app so history keeps working.
### Notes
+- **"Enhanced" is now "AI Summary".** The tab, the toggle and every mention of the generated note now match the **Generate AI Summary** action that produces it, in all 11 locales. (#2163)
- **Generate AI Summary no longer saves your transcript back as the "Enhanced" note.** With an OpenAI reasoning model such as GPT-5.6 Terra, the summary could finish with no error and an Enhanced tab that was just the raw transcript run together. Whenever the model returned no text, the OpenAI provider fell back to handing its input straight back, and the app saved that as the enhanced note. The fallback now only applies to plain dictation cleanup, which its callers already guard; a summary or any other prompted task reports an error instead, including a refusal or a response that ran out of tokens before writing anything. Every other reasoning path, bring-your-own-key, local, enterprise, and OpenWhispr Cloud alike, also reports an error on a blank result rather than saving a blank page. OpenAI's reasoning models additionally get at least 25k output tokens so hidden reasoning cannot crowd out the answer.
+- **Notes open on their AI Summary when one exists.** Clicking a note in the sidebar used to land on the raw notes tab every time, even when a summary had already been generated. A note with an AI Summary now opens on that tab; a note without one still opens on your notes, and the Transcript tab is never the default. The "Notes" tab is also renamed "Your notes" so it reads clearly next to "AI Summary" and "Transcript". (#2196)
- **Detailed Notes gets a shorter, sharper prompt.** The 1.10.0 prompt was three times longer than it needed to be, described the transcript layout incorrectly, ended with a self-check list that added reasoning time, and asked for action items in a shape the editor's owner tagging could never match, so nobody got an owner chip. The rewrite keeps the rules that matter, uses the same `- [ ] Action — Owner` shape as Generate Notes, drops the "Owner not specified" filler, corrects transcription misspellings of names from the participant list and custom dictionary, only lists actions someone actually took on, and says what to do with plain notes that have no transcript. Tested side by side against the old prompt on real meetings of 30, 60, and 90 minutes. Anyone still on the shipped prompt moves to the new one automatically; an edited prompt is left alone.
+- **New note is a split button in the top bar.** `+ New note` creates a note in the current space or folder and starts recording, as before; its chevron adds **Assistant chat**, which opens a fresh conversation on the Chat tab, and **Team space** for anyone who can create one. The button sits right of the search bar next to the window controls on Windows and Linux, and at the far right on macOS. It is hidden during notes onboarding and in the side-panel layout. (#2163)
+- **No more duplicate date headers.** The conversation and overview lists grouped items into Today, Yesterday, Previous 7 days and Older by comparing each item with the one before it, so a list whose timestamps were not perfectly sorted, which happens whenever something updates in the background, showed the same header twice and rendered duplicate keys. Items now land in a fixed set of buckets that come out in order. (#2000, thanks @hsusul)
+
+### Meetings
+
+- **The recording timer survives switching notes.** The elapsed time lived inside the header control, and the editor is rebuilt for each note, so leaving a live recording and coming back restarted the clock at 00:00. The session's start time now lives in the meeting store and the header derives the elapsed time from it, which also stops the timer drifting while the window is throttled. (#2162)
+- **A meeting that ends on its own still offers Generate AI Summary.** The offer was gated on the Transcript tab, and every detected or quick-action meeting opens on your notes, so the one time a meeting ended without you the button was hidden. The offer no longer looks at the open tab. (#2162)
+- **The post-meeting notification is gone.** The card that announced the meeting had ended and offered thirty seconds to restart the recording has been removed. Recordings still stop automatically when the call does and the transcript is saved exactly as before; if a stop fails to persist, the "Recording stopped automatically" toast remains. (#2192)
+- **Windows system-audio capture ignores a stopped helper's last words.** When a capture session was stopped or replaced, stderr output from the old helper process was still fed into the new session, corrupting its buffer and raising errors against the wrong recording. Late output from an inactive helper is now dropped, matching what the macOS capture manager already did. (#2017, thanks @hsusul)
+
+### Team spaces
+
+- **One Settings dialog per space.** A space's menu now opens a single **Settings** dialog with two tabs. **General** holds the name-and-icon field, **Leave space** for members who hold access through a team, and **Delete space** for admins behind the existing type-the-name confirmation. **Members** is the teams-and-members roster: each row has one quiet menu with **Admin**, **Member** and **Remove**, and **Add people** stays collapsed until you search. Opening members from a note's header lands in the same dialog. Names save on blur, Enter or close, and a draft you never touched can no longer overwrite a teammate's rename. The old inline rename, the separate members dialog and the **Change emoji** item are gone. (#2186)
+- **A built-in emoji picker replaces the OS panel.** The system emoji panel behaved differently on every platform and never worked on Linux, which only ever saw a fallback grid. The new picker is searchable and categorised, with keyboard navigation, recents and a **Remove** action, and its labels and search terms are translated into ten languages from emojibase data. Emoji the OS font cannot draw are hidden after a one-time check; country flags are hidden on Windows, which has none. (#2186)
+- **Invite your team from the sidebar.** Workspace owners and admins get an **Invite your team** row above **Get a free month** that opens the existing invitation dialog for their workspace. Members, signed-out users and users with no workspace do not see it, since the invitation call requires the admin role. (#2181)
+- **An existing Screen Recording grant counts as the screen-context opt-in.** Resetting onboarding on macOS no longer shows the row as disabled while the OS permission is already granted. Windows keeps its explicit Enable. (#2186)
+
+### Dictation
+
+- **Windows pins the real microphone again.** Chromium lists the Windows default input twice, once as `default` and once as the `communications` alias, both with the device's own label. The selection code required exactly one label match, saw two, and fell back to Chromium's generic default, which it never caches, so every hotkey press re-resolved the device. Aliases are now ignored when matching, and the device is resolved once when the dictation window loads instead of on the first press. (#2180, thanks @Chadpiha)
+- **Dictation starts listening sooner on Windows.** Pressing the hotkey could take two seconds before the microphone opened. Since 1.9.0 the app pins the system-default microphone to a real device so its health checks can run, and on Windows finding that device means starting a PowerShell process that compiles C# on the fly — a lookup that ran on the first dictation after launch and again whenever an audio device came or went, and expired after 30 seconds either way. The answer is now resolved once at launch, kept until the OS reports a device change, and shared between windows, so the hotkey path only has to open the microphone. (#2178)
+- **Learned corrections skip everyday words.** When you fixed a transcript by swapping one common word for another, such as "why" for "what", the app treated the replacement as a mishearing and saved it to your dictionary. Those entries taught the cleanup model nothing and padded every request. Corrections that resolve to a common English word are no longer learned; names and jargon are unaffected. (#2178)
+- **The dictation pill stops jumping while you talk.** Every live-transcript chunk asked the window to show itself and re-enforce always-on-top, which on Windows and Linux meant a ShowWindow and two SetWindowPos calls against an already visible pill, so the preview flickered and redrew as you spoke. Both calls now run only when the pill is actually hidden, the idiom the other panels already used. (#2185, ported from #1995 by @hsusul)
+- **A cleanup reply the model cut short is no longer pasted.** When cleanup hit its output-token limit, the truncated text was pasted as if it were complete, so a long dictation could end mid-sentence with no warning. Cleanup now requires a complete reply: a truncated or empty one keeps your raw transcript, pastes that instead, and raises the **Cleanup failed** toast with a translated reason. Retrying cleanup from history reports the failure rather than saving the partial text, and Gemini's output cap is removed so a heavy-thinking model cannot trip it. (#2130)
+- **Snippets whose trigger starts with the assistant's name expand instead of waking it.** A trigger such as `openwhispr review` was read as an address to the assistant, which stripped the name and sent "review" off as a command. Any match for the assistant's name that falls inside a snippet trigger is now ignored, in both detection and the address stripping, so the two can never disagree. A trigger that is exactly the bare name still shadows the wake word. (#2153)
+- **Quick actions in the tray and the pill.** The tray menu now leads with **Start listening** / **Stop listening**, **Ask assistant** and **Start meeting recording**, and the dictation pill's right-click menu gains **Start meeting recording** while idle. Each action runs where it belongs: listening goes to the existing dictation start and stop, a meeting goes through the same entry the meeting hotkey uses and brings a live recording forward instead of opening an empty note over it, and only **Ask assistant** asks the renderer, since only it can open the panel. If organisation policy forbids the assistant, or policy is still loading, the pill surfaces and says why. (#2163)
+- **Windows: a dictation started from the tray pastes where you were working.** Starting from the tray captured OpenWhispr's own menu-owner window as the paste target, so the fast-paste helper pulled the foreground onto OpenWhispr, dropped the keystroke and restored the clipboard over your text. A target that is ours but is not one of our real windows is now dropped; the note editor remains a valid target. (#2163)
### Transcription
@@ -25,6 +52,24 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- **Your own Deepgram key works again.** Every Deepgram connection failed with `Unexpected server response: 401`, even though the same key tested fine in Settings and worked against Deepgram directly. Deepgram accepts a raw API key only under its `Token` authorization scheme and reserves `Bearer` for the short-lived tokens OpenWhispr Cloud mints on your behalf — and the app was presenting your key as a `Bearer`. This broke bring-your-own-key dictation as well as Note Recording. (#2140, thanks @nikhilmaddirala)
- **Your own AssemblyAI key works in Note Recording again.** Recordings died seconds in with `Input Duration Violation: 40.0 ms`, followed by a cascade of reconnect errors. AssemblyAI accepts audio in 50-1000 ms frames, and the app measured those frames against dictation's 16 kHz — but Note Recording streams at 24 kHz, where the same frame lasts only 33-40 ms. The frame size now follows the rate each session actually opened at, and an oversized burst — which a busy moment can produce on the system-audio channel — is split instead of being sent as one frame that trips the same limit from the other end. Dictation was never affected. (#2140, thanks @nikhilmaddirala)
- **Local transcription no longer silently drops parts of a recording.** whisper.cpp decodes audio in 30-second windows, and the app was starting whisper-server with `--no-timestamps`. Without timestamp tokens the decoder cannot report where it stopped inside a window, so whisper.cpp skipped to the next 30-second mark regardless and the speech in between was discarded — with no gap or warning, and the surviving text still reading as a complete thought. Dictation was the most exposed, but notes and meeting recordings lost the same words whenever a passage ran up to a window boundary. The 60-character segment wrap that `--no-timestamps` was there to suppress is now switched off directly, so words still never split mid-word. (#2150)
+- **Upload takes video and almost any audio container.** The Upload view refused MPEG audio, video with a speech track (`.mp4`, `.mov`, `.mkv`, `.3gp`) and lossless formats like `.aiff`, `.wma` and `.caf`, even though the bundled FFmpeg decodes every one of them, and dropping such a file did nothing at all. One shared extension list now drives the drop zone and the native file dialog; local engines already decode through FFmpeg, and for OpenWhispr Cloud and bring-your-own-key uploads a container the provider would reject is re-encoded once to mono 16 kHz MP3 on the way out, with the temp file removed afterwards. The nine formats that worked before still upload byte for byte. Files the app cannot read are listed as skipped, with the reason, instead of being ignored. (#2193, fixes #2188)
+- **Uploads and meetings use the local engine you chose in onboarding.** When the upload or meeting scope had no engine of its own it fell back to Whisper, so a fresh install that picked Parakeet or Cohere Transcribe transcribed uploads with Whisper `base`. Unset scopes now inherit the dictation engine, and switching every scope to cloud writes the same provider into all of them. Explicitly choosing Whisper for uploads still sticks. (#2033, thanks @hsusul)
+- **The download tray says Installing once extraction starts.** A local model that had finished transferring sat behind a full bar and a 100% label under a header that still said **Download in progress**, so it read as stalled while it unpacked. The header now says **Installing** with an animated ellipsis, only once every row in the tray has reached that stage, and the animation is skipped when the system asks for reduced motion. (#2137)
+- **Orukeet installs count on Hugging Face.** Orukeet ships as a single archive, which Hugging Face's download counter does not recognise, so the model's real usage was invisible. After a fresh, successful install the app fetches the model's small JSON manifest from the same pinned revision once, in the background, with a three-second timeout and no retries, and saves the published provenance beside the model. Already-installed models, reused archives, cancelled or failed installs and every other model make no request; installation and transcription never wait for it, and the archive's checksum is verified against what the manifest publishes. (#2157, thanks @Nathan-Roll1)
+
+### AI models
+
+- **Local models size their context to the request.** Generate Notes on any meeting over roughly 80 minutes failed with a raw llama.cpp error when Note Formatting used a bundled local model, because every llama-server start was capped at 16384 tokens of context even though all 35 bundled models declare 32768 or more. The cap existed to stop an unbounded context freezing a 16 GB Mac, so it is not raised but derived: the KV cost per token is read from the GGUF itself and the ceiling comes from the memory actually available. A request that still does not fit is refused with a plain sentence naming the model, the tokens it needs and the tokens that fit, rather than a JSON body. (#2155, fixes #2142)
+- **OpenCode Go works as a custom OpenAI-compatible provider.** OpenCode Go routes each conversation by an `x-opencode-session` id and rejected every request without one. A base URL on `opencode.ai` is now recognised by host, the way Mistral, DeepSeek and Cerebras are, and each cleanup or formatting call carries one session id across its endpoint and parameter fallbacks and retries. Other endpoints are unaffected. (#2146, thanks @L4XB, fixes #2145)
+
+### Settings
+
+- **Reset app data restarts the app.** The reset closed the local database and stopped local services, then only reloaded the window, so dictations still pasted but were never saved to history and semantic search stayed down until you quit and relaunched. Reset, and Delete account with device erase, now relaunch the app through the normal quit path. The relaunch drops `--hidden` so a login-started process comes back with a window, drops a stale sign-in deep link so the session the reset just cleared is not restored, defers a downloaded update so it cannot replace the executable mid-restart, and on AppImage hands off to a shell that waits for the mount to release before starting the file again. (#2134, fixes #2132)
+- **The organisation-managed notice sits where it belongs.** The "managed by your organization" banner was inset with no gap before the first section; it now spans the full content width just under the close button, with a shield icon. Opening Settings no longer shows a focused close button: the dialog takes the initial focus itself and the ring appears only for keyboard focus. (#2163)
+
+### CLI
+
+- **List and search endpoints reject bad `limit` and `folder_id` values.** The local CLI bridge converted query parameters with `Number()`, so `?limit=abc` or `?folder_id=-1` became `NaN` or a negative number that flowed straight into SQL and returned an empty 200 rather than an error. Those parameters must now be positive integers and anything else is a 400 `validation_error`, in line with the bridge's error contract. (#2015, thanks @hsusul)
## [1.10.0] - 2026-09-11
diff --git a/package-lock.json b/package-lock.json
index d869d979b..39ae89b51 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
{
"name": "open-whispr",
- "version": "1.10.0",
+ "version": "1.10.1",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "open-whispr",
- "version": "1.10.0",
+ "version": "1.10.1",
"hasInstallScript": true,
"license": "MIT",
"dependencies": {
diff --git a/package.json b/package.json
index 7a78351ad..fccbf9442 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "open-whispr",
- "version": "1.10.0",
+ "version": "1.10.1",
"description": "A desktop dictation application using whisper.cpp for speech-to-text transcription",
"main": "main.js",
"private": true,
diff --git a/src/components/notes/NoteEditor.tsx b/src/components/notes/NoteEditor.tsx
index f19dc60b6..4cdff660f 100644
--- a/src/components/notes/NoteEditor.tsx
+++ b/src/components/notes/NoteEditor.tsx
@@ -245,7 +245,8 @@ export default function NoteEditor({
}: NoteEditorProps) {
const { t } = useTranslation();
const locale = useUiLocale();
- const [viewMode, setViewMode] = useState<MeetingViewMode>("raw");
+ const defaultViewMode: MeetingViewMode = enhancement ? "enhanced" : "raw";
+ const [viewMode, setViewMode] = useState<MeetingViewMode>(defaultViewMode);
const [chatMode, setChatMode] = useState<EmbeddedChatMode>("hidden");
const [folderSearch, setFolderSearch] = useState("");
const [isCreatingFolder, setIsCreatingFolder] = useState(false);
@@ -501,14 +502,14 @@ export default function NoteEditor({
setDiarizedSegments(null);
setIsDiarizing(false);
setSpeakerMappings({});
- setViewMode("raw");
+ setViewMode(defaultViewMode);
if (titleRef.current && titleRef.current.textContent !== note.title) {
titleRef.current.textContent = note.title || "";
}
editorRef.current?.commands.focus();
});
}
- }, [note.id, note.title, scheduleUiUpdate]);
+ }, [note.id, note.title, defaultViewMode, scheduleUiUpdate]);
useEffect(() => {
window.electronAPI?.getSpeakerMappings?.(note.id).then((mappings) => {
diff --git a/src/locales/ar/translation.json b/src/locales/ar/translation.json
index 8c2a04d0e..fe0c81f0f 100644
--- a/src/locales/ar/translation.json
+++ b/src/locales/ar/translation.json
@@ -1619,7 +1619,7 @@
"staleIndicator": "تم تغيير المحتوى منذ التحسين",
"live": "مباشر",
"transcript": "النص المفرَّغ",
- "notes": "الملاحظات",
+ "notes": "ملاحظاتك",
"conversationWillAppear": "ستظهر المحادثة هنا...",
"linkedEvent": "الحدث المرتبط",
"noFolder": "بدون مجلد",
diff --git a/src/locales/de/translation.json b/src/locales/de/translation.json
index 8c269110c..bdc79c0a7 100644
--- a/src/locales/de/translation.json
+++ b/src/locales/de/translation.json
@@ -3278,7 +3278,7 @@
"staleIndicator": "Der Inhalt hat sich seit der Verbesserung geändert",
"live": "Live",
"transcript": "Transkript",
- "notes": "Notizen",
+ "notes": "Ihre Notizen",
"conversationWillAppear": "Gespräch wird hier angezeigt...",
"linkedEvent": "Verknüpftes Ereignis",
"noFolder": "Kein Ordner",
diff --git a/src/locales/en/translation.json b/src/locales/en/translation.json
index 8f2f77870..e8f6aaea7 100644
--- a/src/locales/en/translation.json
+++ b/src/locales/en/translation.json
@@ -3278,7 +3278,7 @@
"staleIndicator": "Content has changed since enhancement",
"live": "Live",
"transcript": "Transcript",
- "notes": "Notes",
+ "notes": "Your notes",
"conversationWillAppear": "Conversation will appear here...",
"linkedEvent": "Linked event",
"noFolder": "No folder",
diff --git a/src/locales/es/translation.json b/src/locales/es/translation.json
index 27441b2b8..ef3769028 100644
--- a/src/locales/es/translation.json
+++ b/src/locales/es/translation.json
@@ -2988,7 +2988,7 @@
"staleIndicator": "El contenido ha cambiado desde la mejora",
"live": "En vivo",
"transcript": "Transcripción",
- "notes": "Notas",
+ "notes": "Tus notas",
"conversationWillAppear": "La conversación aparecerá aquí...",
"linkedEvent": "Evento vinculado",
"noFolder": "Sin carpeta",
diff --git a/src/locales/fr/translation.json b/src/locales/fr/translation.json
index 248fbb292..2d0412aec 100644
--- a/src/locales/fr/translation.json
+++ b/src/locales/fr/translation.json
@@ -3278,7 +3278,7 @@
"staleIndicator": "Le contenu a changé depuis l'amélioration",
"live": "En direct",
"transcript": "Transcription",
- "notes": "Notes",
+ "notes": "Vos notes",
"conversationWillAppear": "La conversation apparaîtra ici...",
"linkedEvent": "Événement lié",
"noFolder": "Aucun dossier",
diff --git a/src/locales/it/translation.json b/src/locales/it/translation.json
index a67716182..c30cbf946 100644
--- a/src/locales/it/translation.json
+++ b/src/locales/it/translation.json
@@ -2935,7 +2935,7 @@
"staleIndicator": "Il contenuto è cambiato dall'ultimo miglioramento",
"live": "Dal vivo",
"transcript": "Trascrizione",
- "notes": "Note",
+ "notes": "Le tue note",
"conversationWillAppear": "La conversazione apparirà qui...",
"linkedEvent": "Evento collegato",
"noFolder": "Nessuna cartella",
diff --git a/src/locales/ja/translation.json b/src/locales/ja/translation.json
index 1d65dedb7..5d924fcd7 100644
--- a/src/locales/ja/translation.json
+++ b/src/locales/ja/translation.json
@@ -2810,7 +2810,7 @@
"staleIndicator": "強化後にコンテンツが変更されました",
"live": "ライブ",
"transcript": "文字起こし",
- "notes": "ノート",
+ "notes": "あなたのノート",
"conversationWillAppear": "会話がここに表示されます...",
"linkedEvent": "リンクされたイベント",
"noFolder": "フォルダなし",
diff --git a/src/locales/pt/translation.json b/src/locales/pt/translation.json
index 3144156ba..9192ae571 100644
--- a/src/locales/pt/translation.json
+++ b/src/locales/pt/translation.json
@@ -2935,7 +2935,7 @@
"staleIndicator": "O conteúdo mudou desde o aprimoramento",
"live": "Ao vivo",
"transcript": "Transcrição",
- "notes": "Notas",
+ "notes": "Suas notas",
"conversationWillAppear": "A conversa aparecerá aqui...",
"linkedEvent": "Evento vinculado",
"noFolder": "Sem pasta",
diff --git a/src/locales/ru/translation.json b/src/locales/ru/translation.json
index b84be5ac0..595b5f385 100644
--- a/src/locales/ru/translation.json
+++ b/src/locales/ru/translation.json
@@ -2957,7 +2957,7 @@
"staleIndicator": "Содержимое изменилось после улучшения",
"live": "Живой",
"transcript": "Транскрипция",
- "notes": "Заметки",
+ "notes": "Ваши заметки",
"conversationWillAppear": "Разговор появится здесь...",
"linkedEvent": "Связанное событие",
"noFolder": "Без папки",
diff --git a/src/locales/zh-CN/translation.json b/src/locales/zh-CN/translation.json
index 35776f6e7..2d0edade0 100644
--- a/src/locales/zh-CN/translation.json
+++ b/src/locales/zh-CN/translation.json
@@ -2935,7 +2935,7 @@
"staleIndicator": "内容在增强后已更改",
"live": "实时",
"transcript": "转录",
- "notes": "笔记",
+ "notes": "你的笔记",
"conversationWillAppear": "对话将显示在这里...",
"linkedEvent": "关联日程",
"noFolder": "无文件夹",
diff --git a/src/locales/zh-TW/translation.json b/src/locales/zh-TW/translation.json
index 596f5036e..f312e5c46 100644
--- a/src/locales/zh-TW/translation.json
+++ b/src/locales/zh-TW/translation.json
@@ -2935,7 +2935,7 @@
"staleIndicator": "內容在增強後已變更",
"live": "即時",
"transcript": "轉錄",
- "notes": "筆記",
+ "notes": "你的筆記",
"conversationWillAppear": "對話將顯示在這裡...",
"linkedEvent": "關聯行程",
"noFolder": "無資料夾",