Versions:
Sussurro IA is a voice dictation tool for Windows, published by RobertoB, that types spoken words directly into the field the user is already working in. Rather than offering a separate scratchpad to copy text from, the software inserts transcriptions into whatever field has focus at the moment of use, whether that is an email compose window, a search box, a terminal, or a comment box in another application. The workflow is built around a global shortcut: the user holds the key, speaks, releases it, and the transcribed text appears in place. A second shortcut delivers the same dictation translated into English, Spanish, or German, or rewritten as a well-formed prompt for a language model. Dictation itself is in Italian, and spoken commands convert words into what they represent, so saying "a capo" produces a line break, "nuovo paragrafo" produces a blank line, and "emoji sorriso" produces an emoji. Privacy is handled by design: audio is transmitted only while the shortcut is held, and only to the transcription service the user configures with their own API key, with Groq as the default and any OpenAI-compatible endpoint as an alternative. Nothing is sent to the program's author, as there is no telemetry, no usage statistics collection, and no update check. The software falls into the productivity and speech-to-text category, with use cases that include hands-free text entry across applications, multilingual communication, and prompt drafting for language models. The current version is 1.0.1, and two versions have been released so far. Sussurro IA is beta software, free to use but not open source. Because it is not code-signed, Windows SmartScreen displays a warning on first run, which users should expect during initial setup.
Tags: