VocalCode is a dictation tool that transcribes speech directly into code editors and text fields on Windows and macOS using on-device AI models—no cloud upload.
It costs $4.99 as a permanent one-time purchase with no recurring fees, includes a free 30-day trial, and supports Mandarin Chinese and 25 European languages alongside English, making it useful for developers across regions who want private speech input.
What happened
VocalCode, a desktop dictation tool, lets developers speak code and prose directly into editors, terminals, and chat windows using on-device speech recognition. The tool costs $4.99 as a one-time purchase (no subscription), includes a 30-day free trial, and works on up to 3 devices.
Why it matters
Speech recognition runs entirely on your CPU—audio never leaves your computer—making it useful for developers who want privacy-preserving hands-free input. The tool supports Mandarin Chinese and 25 European languages via auto-detecting models, plus English, so teams across regions can use it without uploading speech data to the cloud.
What to watch
VocalCode requires macOS 11 or later on Apple Silicon, or Windows; the 25 European language options are model-supported previews pending per-language testing. After the initial model download, recognition works fully offline; revalidation of the paid licence happens online at least every 30 days.
Ask the AI about this article →
VocalCode addresses a practical gap in developer tooling: dictation that preserves privacy and requires no subscription. By running speech recognition on the user's own CPU rather than uploading audio to a cloud service, it eliminates the privacy trade-off that has historically come with voice input tools. The $4.99 one-time purchase model also avoids the friction of recurring payments or account creation, lowering the barrier to adoption for individual developers and small teams.
The breadth of language support—particularly the inclusion of Mandarin Chinese alongside 25 European languages via a shared auto-detecting model—signals an attempt to serve non-English-speaking development communities. However, the absence of East and Southeast Asian languages beyond Mandarin (no Cantonese, Korean, Japanese, Thai, or Vietnamese) suggests a deliberate scope boundary. The description of the 25 European options as "preview labels pending per-language product testing" indicates the product is still maturing in non-English regions, so users in those markets may encounter rough edges.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Mitsubishi Electric and its U.S
AI coding has moved through three stages—prompt engineering, context engineering, and now harness engineering—…
Workday is integrating its AI agents with Google Cloud's Gemini Enterprise, letting employees start tasks like…
Over the last two years, writing code syntax has become much easier, with tools like Cursor, Claude Code, and…
Meta released Pocket, a mobile app that lets users create interactive games and 'gizmos' by typing text prompt…
Z.ai, a Beijing-based AI startup, made public the details of its latest model on Friday
