MosMos is a speech-to-text tool whose core philosophy is "speak naturally, get usable text instantly." According to its official website, people speak faster than they type, and MosMos turns speech directly into text.
Uses
- Instantly convert spoken language into text usable in chats, emails, documents, or terminals.
- In meeting scenarios, continuously transcribe, identify speakers, and generate summaries and to-dos after the meeting ends.
Main capabilities
- Scenario-adaptive writing style: MosMos automatically adjusts the writing style based on the usage scenario, and the style can be changed at any time. In the example, colloquial expressions are organized into more concise, formal text.
- Control over the degree of preserving the original voice: Provides three levels—Basic, Standard, and Advanced—letting the user decide how much of the original spoken expression to preserve.
- Custom vocabulary: English proper nouns, homophones, and personal names can be added to the vocabulary so that MosMos prioritizes recognizing them and preserves these words during polishing. In the example, proper nouns such as Jordon/Jordan, Nimbis/Nimbus, and Figmar/Figma can be correctly recognized and preserved.
- Multi-speaker transcription: Identifies different speakers and preserves the full context.
- Meeting summary: Organizes the meeting background, participants, and key points.
- To-do extraction: Extracts clear to-dos, owners, and deadlines.
How to use Official website describes shortcut actions:
- Click any text input field to use it in chats, emails, documents, or terminals without leaving the current application.
- Press the Fn key once to start speaking, without needing to dictate punctuation or organize formal wording in advance; press it again, and MosMos detects the context, applies keywords, polishes the text, and pastes it.
- Press Fn + Shift to record a meeting: continuously transcribe, identify speakers, and generate a summary and to-dos after the meeting ends.
- Press Right Alt once to start speaking; press Alt + M to record a meeting. The official website mentions "one key, two uses" and "two shortcuts, two uses," but does not specify the correspondence for each platform.
Applicable scenarios
- Daily quick input: voice typing in any text box such as chats, emails, documents, and terminals.
- Meeting notes: multi-person meeting transcription, speaker identification, post-meeting summaries, and task organization.
- Industry or team communication that requires preserving proper nouns.
Limitations The official website does not provide specific information about supported platforms, pricing, language support scope, offline or online processing methods, privacy policy, data storage methods, accuracy metrics, etc., and none is currently provided.