Quick Dictation
Hold ⌃⌥X anywhere. Saransh transcribes locally, pastes into the focused field, and never saves to your library.
Local-first · macOS 14+
Speak. Capture. Structure.
Local-first menu bar notepad for macOS. Dictate into any app with app-aware formatting, capture conversations (optional meeting audio) with on-device Whisper, enhance with cloud or local AI, and let agents read notes over opt-in MCP.
14-day full trial · One-time purchase · Microphone & Accessibility required; Calendar and meeting audio optional
Saransh is a product of Kitto Byte, a California corporation.
Saransh — AI Note
Team sync recap
Recorded · On-device Whisper
Summary
Discussed launch timeline, onboarding flow, and local-first privacy positioning.
- ☑Ship website redesign
- ☐Record demo screenshots
⌃⌥X DictateContext modes⌃⌥R RecordMeeting audioLocal MCP
Features
Built for how you actually work
Dictate with app-aware formatting, capture both sides of a call when you opt in, enhance with cloud or local AI, and let agents read your Conversations over local MCP.
App-aware context modes
Auto-format by frontmost app: Polish, Email, Notes, To-do, or Agent prompt — plus custom profiles you bind to bundle IDs. Unbound apps use Polish. Overlay shows the active mode.
Conversations
Press ⌃⌥R to record a session, or start from an opt-in calendar meeting prompt. Each conversation becomes a searchable note in Saransh.
Capture meeting audio
Opt in to mix microphone with system audio so remote participants are included. Requires Screen & System Audio Recording (audio only — no screen video stored). Quick Dictation stays mic-only.
Calendar meeting prompts
Opt in to read macOS Calendar via EventKit. At meeting start, Saransh shows an on-screen Start/Skip prompt — recording never begins until you tap Start. Optionally auto-stop when the calendar event ends. No meeting bots.
On-device Whisper
Speech stays on your Mac. Choose Fast, Balanced, or Best Accuracy; the model downloads once on first launch. Add vocabulary hints and replacements in Settings → Speech for names and jargon.
AI notes — cloud or local
Enhance with OpenAI, Anthropic, Gemini (BYOK), or keep it local with Ollama, LM Studio, or Apple Intelligence. Templates include Meeting Recap, Action Items, and more. Preview markdown with interactive task checklists.
Speaker diarization
Label speakers as Speaker 1, Speaker 2, and so on — on-device. Rename, merge, or reassign turns in the transcript.
Local MCP for agents
Opt in from Settings → Agents. Cursor and Claude Desktop can list, search, and read Conversations over stdio on this Mac — read-only, nothing uploaded. Quick Dictation is never exposed.
Full-text search
Find anything instantly across note titles, transcripts, and AI note bodies with SQLite FTS5.
Markdown export
Export a raw transcript or any AI note as a `.md` file. Optionally auto-export Conversations to a folder (e.g. an Obsidian vault). Markdown stays the source of truth.
Vocabulary & replacements
Teach Whisper your names and jargon, then apply deterministic find→replace after transcription — for Quick Dictation and Conversations alike.
1
Dictate
Hold a shortcut and speak — context modes format for Email, Agent prompt, and more.
2
Capture
Record conversations with speaker labels, optional meeting audio, or calendar Start prompts.
3
Enhance
Run a template with cloud or local AI, export markdown, or connect agents via MCP.
Privacy
Local-first by design
Your voice and notes stay on your Mac unless you explicitly send text to a cloud AI provider you choose — or keep enhance fully local.
100%
On-device transcription
Whisper runs locally on your Mac
0
Kitto Byte cloud archive
We do not host your notes or recordings
Local+
Optional AI enhance
Cloud BYOK or Ollama / LM Studio / Apple Intelligence
Keychain
Secrets storage
License and API keys stay in macOS Keychain
Pricing
Lifetime license
$59 one time
- 14-day full trial on first launch
- Unlimited dictation & conversation capture
- App-aware context modes for Quick Dictation
- Vocabulary hints & replacements
- Opt-in calendar Start/Skip prompts
- Opt-in meeting audio (mic + system audio)
- AI enhance via cloud BYOK or local models
- Opt-in local MCP for Cursor & Claude Desktop
- Free updates for v1.x
No subscription. Activate with the key from your purchase email.
Setup
Getting started
Up and running in minutes. Most of the wait is the one-time speech model download.
- 1Download the DMG and drag Saransh to Applications.
- 2Grant Microphone and Accessibility permissions during onboarding.
- 3Wait for the speech model download (first launch only).
- 4Optionally enable calendar meeting prompts or Capture meeting audio in Settings → Conversations.
- 5Optionally bind apps to context modes (Email, Agent prompt, and more) in Settings → Quick Dictation.
- 6Add a cloud API key or choose Ollama / LM Studio / Apple Intelligence if you want AI notes or formatting.
- 7Optionally add vocabulary & replacements in Settings → Speech, and enable local MCP in Settings → Agents.
- 8Activate your license key from the purchase email before the trial ends (Settings → License).
FAQ
Common questions
Quick answers before you download. More detail is in our privacy and terms pages.
What are the system requirements?
macOS 14 or later. Saransh needs Microphone and Accessibility permissions. Calendar and Notifications are optional (meeting prompts). Screen & System Audio Recording is optional (Capture meeting audio). Internet is required on first launch to download the on-device Whisper speech model. An AI provider is optional and only needed for AI notes or dictation formatting — cloud BYOK (OpenAI, Anthropic, Gemini) or local (Ollama, LM Studio, Apple Intelligence).
What permissions does Saransh need?
Microphone for dictation and conversation capture, and Accessibility to paste transcribed text into the app you are using. Calendar and Notifications are requested only if you enable meeting prompts. Screen & System Audio Recording is requested only if you enable Capture meeting audio — Saransh uses audio only and does not store screen video.
How do calendar meeting prompts work?
The feature is off by default. When enabled, Saransh reads timed events from macOS Calendar (including Google or Outlook accounts already synced there). At meeting start it shows an on-screen Start/Skip prompt — recording never begins until you tap Start. You can optionally auto-stop when the calendar event ends. Saransh does not join calls as a bot.
Can I fix names and jargon in transcripts?
Yes. In Settings → Speech, add vocabulary words as Whisper recognition hints and set replacements (e.g. misspelled names → correct spelling). Replacements apply after transcription for both Quick Dictation and Conversations.
Can Saransh capture both sides of a call?
Yes, when you enable Capture meeting audio in Settings → Conversations. Conversations then mix your microphone with system audio so remote participants are included. This requires Screen & System Audio Recording permission. Quick Dictation stays microphone-only. You are responsible for complying with local consent and recording laws.
What are context modes?
Quick Dictation formats what you said using instruction profiles bound to apps (by bundle ID). Built-ins include Polish (default for unbound apps), Email, Notes, To-do, and Agent prompt. You can edit instructions and add custom profiles in Settings → Quick Dictation. Formatting needs a configured AI provider; without one, Saransh pastes the raw transcript.
Which Whisper model should I use?
Saransh offers three on-device tiers in Settings: Fast (~140 MB) for the quickest download and lowest latency, Balanced (~630 MB) as the recommended speed/accuracy tradeoff, and Best Accuracy (~626 MB) for the highest transcription quality. Each tier downloads once; switch anytime in Settings or the menu bar.
Does my audio leave my Mac?
Transcription runs on-device with Whisper. Audio and transcripts stay in your local SQLite database. If you use a cloud AI provider for enhance or dictation formatting, transcript text is sent to that provider with your API key. Ollama, LM Studio, and Apple Intelligence keep that step local.
Do I need an API key?
No. Dictation and conversation capture work without one. Add an OpenAI, Anthropic, or Gemini key only if you want cloud AI formatting or notes. Or choose Ollama, LM Studio, or Apple Intelligence in Settings for local enhance and formatting with no cloud key.
What is local MCP?
An opt-in, read-only connector for Cursor and Claude Desktop. Enable Allow local MCP for agents in Settings → Agents, copy the config into your client, and agents can list, search, and read Conversations over stdio on your Mac (`Saransh --mcp`). Nothing is uploaded. Quick Dictation is never exposed.
How does the trial work?
You get a 14-day full trial on first launch with no feature limits. After that, capture and enhance require a lifetime license activated from your purchase email.
How do I activate my license?
Open Settings → License in Saransh and paste the key from your Lemon Squeezy purchase email. Activation validates with Lemon Squeezy over the network.
What is your refund policy?
Saransh includes a 14-day full trial before you buy. After purchase, lifetime licenses are non-refundable except for billing errors, activation issues we cannot resolve, or where required by law. See our Refund Policy for details.
Ready to speak your notes?
Download Saransh, try every feature for 14 days, and keep your transcripts local on your Mac.