Voice typing across apps
Speak into any active text field and press Fn again to finish; MosMos converts the recording into text and inserts it without requiring manually dictated punctuation.
MosMos
MosMos is a voice-to-text tool for macOS 15+ that adapts speech to chats, email, documents, code and terminal workflows, with meeting transcripts, takeaways and to-dos.
Voice typing and meeting notes from natural speech
MosMos is a voice-to-text productivity tool for turning natural speech into text in active text fields. It is designed for chats, emails, documents, and terminal workflows, allowing users to speak rather than compose every sentence by keyboard.
The product combines transcription with context-aware writing styles and selectable refinement. It can preserve spoken wording, improve grammar and flow, or create a shorter draft, while custom keywords help protect names and specialized terms. A separate meeting mode records continuously, identifies speakers, and organizes the result into a transcript, key takeaways, and to-do items.
Features
Context-aware writing
MosMos adapts writing style to the current scenario, with examples on the site including Lark, WeChat, email, documents, code, and terminal workflows.
Three refinement levels
Select Basic to preserve the original wording, Standard to improve grammar and flow, or Advanced to produce a concise draft.
Custom keywords
Add English proper nouns, homophones, and names to a custom vocabulary so they are recognized and preserved during refinement.
Meeting transcription and follow-up
Use Fn + Shift to continuously record a meeting, identify speakers, preserve the transcript, and generate key takeaways and to-do items afterward.
Keyboard-first workflow
The workflow uses keyboard shortcuts: Fn starts and ends voice typing, while Fn + Shift starts meeting recording.
Use cases
Chat and workplace messages
Speak a message directly into a chat or collaboration tool, then let MosMos adjust the wording to suit the selected context before insertion.
Email and document drafting
Draft emails and documents verbally when keyboard composition is slower, choosing whether to retain the spoken phrasing or produce a more polished version.
Code and terminal input
Use the voice workflow in coding and terminal contexts where context-specific writing style can help turn spoken instructions or notes into text without leaving the active app.
Meeting follow-up
Record a meeting with Fn + Shift and use the resulting speaker-separated transcript, key takeaways, and to-do items as a follow-up record.
Specialized names and terminology
Add recurring names, product terms, or easily confused words to the custom vocabulary when accurate recognition matters during refinement.
Pros and Cons
Pros
- Supports voice input in any active text field across common writing and terminal contexts.
- Lets users control how closely the output follows their original speech.
- Provides custom vocabulary support for names, proper nouns, and homophones.
- Combines meeting transcription with speaker identification, summaries, and to-do items.
- Uses simple Fn-based shortcuts for both dictation and meeting recording.
Cons
- The currently listed availability is limited to macOS 15+; Windows and iOS are marked as coming soon.
- The available site content does not specify pricing, supported languages beyond the examples provided, privacy behavior, or a full list of app integrations.
FAQ
How does MosMos voice typing work?
MosMos is used by clicking into a text field, pressing Fn once to start speaking, and pressing Fn again to finish. It then applies the selected context and refinement settings before inserting the text.
Which platforms does MosMos support?
The site lists macOS 15+ as available. Windows and iOS are shown as coming soon.
How much can MosMos change my original wording?
You can choose among Basic, Standard, and Advanced refinement. Basic keeps the wording as spoken, Standard improves grammar and flow, and Advanced rewrites it as a concise draft.
What contexts or writing styles does MosMos support?
MosMos can use the current context, including examples such as Lark, WeChat, email, documents, code and terminal, to adapt its writing style. The site does not provide a complete integration list.
Can MosMos create meeting notes?
Pressing Fn + Shift starts meeting recording. MosMos transcribes continuously, identifies speakers, and produces a meeting summary and to-do items when the meeting ends.
Quick Facts
- Category
- Voice typing and meeting transcription
- Available platform
- macOS 15+
- Coming soon
- Windows and iOS
- Voice typing shortcut
- Fn to start; Fn again to finish
- Meeting shortcut
- Fn + Shift
- Refinement modes
- Basic, Standard, Advanced
MosMos Alternatives
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. Dictate into any app, use Flow, cleanup, translation, and a screen-aware assistant.
QuickQuill
QuickQuill is a local-first macOS dictation and transcription app to record meetings, summarize audio, and export notes without the cloud.
Zen Whisper
Zen Whisper is a local-first dictation and transcription app for Apple Silicon Macs on macOS 14+. Dictate into most Mac text fields and transcribe media or supported public links across 110 languages.
Speech to Text Converter
Speech to Text Converter is a browser-based transcription tool for live dictation and uploaded audio or video files. Free for short tasks, Pro offers unlimited transcription, AI summaries, translation, speaker ID, and advanced exports.
CAKIE
CAKIE is a Mac app for recording your screen and voice for an AI agent, with transcripts, screenshot highlights, and easy prompt copying.
Sanota
Sanota turns spoken memories and interviews into clear written stories for personal storytelling, family history and shared memories, with guided prompts and subscriptions.