project
SayIt - an open-source AI voice input method that automatically converts spoken language into written expression.
SayIt is an open-source AI voice input method built on Rust and supports Windows desktop. Users can press and hold a shortcut key to speak, and their spoken words will be converted into usable written text in real time.
What is SayIt?
SayIt is an open-source AI voice input method built on Rust and supporting Windows desktop. Users can press and hold a shortcut key to speak, and their spoken words will be converted into usable written text in real time. The product offers three voice recognition modes: local, cloud API, and server. It has a built-in AI processing engine that can automatically remove filler words, correct typos, organize word order, and translate between Chinese and English. It also supports automatic matching of Prompt rules based on the application, balancing efficiency and privacy.
SayIt's main functions
- Speech transcriptionIt supports three speech recognition modes: local, cloud API, and server, balancing privacy, accuracy, and hardware requirements as needed.
- AI sortingIt has three built-in polishing modes: intent organization, faithful proofreading, and Chinese-English translation, which automatically transform spoken language into logically clear written expression.
- Application rulesAutomatically matches Prompt rules based on the application where the cursor is located, and is compatible with common software such as Teams, Outlook, VSCode, Cursor, and Notepad.
- Hot word customizationIt supports custom hot word libraries, effectively improving the recognition accuracy of professional terms, personal names and proper nouns.
- Theme appearanceOffers light, dark, and warm color themes and various floating window styles, and supports custom waveforms and window lengths.
Follow us on WeChat and reply with "open source",join inAI open source project discussion group
How to use SayIt
-
Download and installVisit the SayIt official website https://sayitapp.site to download the Windows client and complete the installation.
-
Mode SelectionUpon first launch, you will be taken to the speech engine page. You can switch between local, cloud API, or server modes as needed.
-
Configure shortcut keysBy default, the Alt key to the right of the space bar is used as the voice trigger key, but this can be customized in the settings.
-
Start speakingPress and hold the shortcut key in any text box and speak into the microphone; the edited text will be automatically inserted when you release the key.
-
View historyOn the history page, click to expand details to trace back the original transcription, the model used, the audio length, and the recognition time.
SayIt's core advantages
-
Privacy FirstSupports pure local recognition and self-hosted deployment; audio data does not leave the device or is deleted immediately after processing.
-
Open source and transparentThe front-end and back-end code are completely open source, using the AGPL-3.0 license, and are auditable and support community co-construction.
-
Lightweight and safeThe client is built on Rust, which has low resource consumption, stable operation and high security.
-
Intelligent organizationAI automatically converts spoken language into written language, supporting various polishing modes such as segmentation, translation, and removal of colloquialisms.
-
Scene adaptationAutomatically switch Prompt rules based on the current application, seamlessly integrating into workflows such as Teams, Outlook, and VSCode.
SayIt's project address
- Project official websitehttps://sayitapp.site/
- GitHub repositoryhttps://github.com/crosswk/SayIt
Comparison of SayIt's similar competing products
| Comparison Dimensions | SayIt | AudioClaw (SenseTime) |
|---|---|---|
| Product Positioning | Open-source AI voice input method, focusing on speech-to-text conversion on desktop devices. | SenseTime's AI voice input tool focuses on intelligent input across multiple devices. |
| Deployment method | Supports three modes: local, cloud API, and self-hosted server; fully open source. | Primarily relies on cloud services, closed-source products |
| Privacy protection | In local mode, data does not leave the device; in server mode, processed data is not retained and can be self-hosted. | Primarily relies on cloud processing; privacy policies are controlled by the service provider. |
| AI sorting | Built-in multiple polishing modes, supports application-level Prompt rule customization | It focuses on speech recognition and basic input assistance, with relatively limited AI processing capabilities. |
Application scenarios of SayIt
-
Office documentsQuickly compose emails, documents, and code comments in software such as Word, Outlook, and VSCode, improving input efficiency.
-
Meeting minutesIt converts meeting speeches into structured minutes in real time, automatically organizes them into bullet points, and removes redundant interjections.
-
Cross-language communicationIt allows users to speak Chinese while simultaneously outputting English text, facilitating international team collaboration and the creation of foreign language content.
-
Content creationIt provides self-media authors and novelists with the ability to dictate their writing, which is then automatically transcribed into coherent articles by AI.
-
Accessible InputIt provides an efficient voice input alternative for users who have difficulty typing or whose hands are not handy, thus lowering the barrier to entry.