Rubil
Voice dictation for Gmail, Slack, Notion + 20 apps. Auto-formats your speech. Audio never stored. 1000 words free daily.
Voice dictation for every web app you use. Speak naturally — Rubil formats your speech into clean, ready-to-send text. Properly structured emails. Concise chat messages. Clean document prose. Works across 20+ web apps where knowledge workers spend their day. No cleanup. No rewrites. No copy-paste. No post-editing.
Audio is processed instantly through secure transcription and never stored. No transcript history. No voice files on our servers. Your glossary is encrypted both on your device and in the cloud.
Teach Rubil your world. Add names, acronyms, and jargon once. Rubil applies them every time you dictate.
Voice dictation and voice typing in one click:
1) Hit the mic
2) Speak naturally — ramble, self-correct, think out loud
3) Rubil formats your speech and drops it right in. Done.
Free: 1,000 words/day. Pro: $9/mo for unlimited.
Learn more about Rubil
FluidVoice
FluidVoice is a free, open source macOS dictation app that pairs local speech recognition with Fluid-1, an on-device AI model for polishing dictation. One hotkey lets users speak into any text field across email, documents, chat, terminals, code editors, and other apps, with text appearing in near real time. Local speech models keep dictation on-device and work offline, while optional AI post-processing can use Fluid Intelligence, OpenAI, Groq, or custom providers. Fluid-1 cleans up rough dictation, fixes formatting, capitalization, dates, names, and numbers, and adapts tone to the active app without changing the speaker’s meaning. Users can create custom prompts for different apps, while Write Mode, Command Mode, and Direct Dictation make it easy to switch contexts. FluidVoice supports more than 40 languages across models including Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v2 and v3, Cohere Transcribe, Apple Speech, and Whisper.
Learn more about FluidVoice
JotMic
JotMic is dictation for people who would rather talk than type. Hold one key, say what you mean, and finished writing lands where your cursor already is - in Gmail, Slack, Docs, your editor or any other app, with the commas, full stops and capitals already in place.
It takes out the ums and false starts and leaves every other word as you said it, so what arrives is ready to send rather than ready to edit. Teach it a name, an acronym or a piece of jargon once and it keeps landing right on both your machines. It picks up 99+ languages as you speak.
On a Mac it goes further and runs your computer: say what you want done - open something, switch to it, hit a menu item - and it happens. Drop in a recording and get clean text or subtitles back.
Free to start, no card. Mac and Windows, one account.
Learn more about JotMic
DictaFlow
DictaFlow is an AI dictation app for Windows, Mac, iPhone, and Android via Telegram that turns messy speech into clean text wherever the cursor is. Hold a keyboard shortcut, mouse button, or VDI-safe trigger, speak naturally, and release to insert text directly into email, documents, IDEs, EHRs, browsers, terminals, notes, and remote desktops. It is built for the messy parts of dictation, including names, acronyms, code terms, drug names, clinical shorthand, contract language, accents, and more than 100 languages. DictaFlow understands mid-sentence corrections such as “actually” and “I mean,” so users can fix mistakes without breaking rhythm, and AI cleanup can turn rough speech into emails, bullets, code comments, meeting notes, prompts, or formatted text as they talk. Users can also highlight existing text in apps such as Word, Slack, or VS Code and edit it by voice.
Learn more about DictaFlow