Voice input for a blogger

Potok transcribes Russian speech; this site has been translated into English for convenience.

Writing a video script, a post or a video description? Dictating the text by voice is often faster than typing it by hand. Potok (potok.now) has a model trained for Russian speech, including terms like call to action; it places punctuation and capital letters itself; and its dictation speed is about 900 characters per minute.

You have shot the video, but the text for it is still not written: you need a script for the next shoot, a post for the video and a short description for the platform. All of this is usually typed by hand between editing and shooting, taking time that is better spent on the content itself.

A working day with dictation

A video script is often born as a stream of thoughts, and it is easier to speak out a draft than to phrase it straight away in a text editor. You hold Potok's hotkey, talk through the idea of the video from start to finish, and release. The text appears right in the document, where the cursor is, and all that is left is to split it into scenes and adjust the wording.

With a post for the video or a description of it, the logic is the same: you can dictate a first version of the text right after the shoot, while the wording is still fresh in your head, without even opening the keyboard. Potok inserts the dictation into the field where you are working now, whether it is notes, a document or a publishing form in the browser, and places punctuation and capital letters itself, so you do not have to dictate “tochka” (period) and “zapyataya” (comma) separately.

If the text contains English words and phrases, and in a blogger's work they come up often, you can say them right inside a Russian phrase without switching the language: Potok's model is trained on mixed Russian and English speech.

Terms: what is recognized without a dictionary

In a blogger's work, terms like "the hook at the start of the video", call to action or "audience engagement" come up constantly: a mix of Russian wording and English expressions that often go in one phrase. Potok's model is trained for Russian speech, including terms and Russian with English. You do not need to switch the language, and rare names and titles are added to the personal dictionary on the Pro plan.

Potok also has a separate personal dictionary. It is a paid Pro feature, needed more for unusual names, brand names or your own abbreviations that are not in ordinary speech, and not for generally accepted terms like a hook or call to action. How voice input helps with similar terminology in another profession can be seen in the article voice input for programmers.

Where Potok will not suit a blogger

If you need not to dictate new text but to transcribe an interview or a voice note that is already recorded in another file, Potok does not fit: it has no transcription of files and recordings, and it recognizes only what is said into the microphone while the hotkey is held. Potok also has no apps for Android and iPhone, so you cannot dictate a post from a phone on the road, and it has no voice commands for editing text: you have to fix a mistake in the dictated text with the keyboard.

Potok is a cloud service, recognition runs on servers in Russia, and it does not work without the internet, so for shoots in places with no connection it is worth putting dictation off until you are back online.

A general overview of voice input for work is in the section voice input for work.

Frequently asked questions

Built-in dictation and Potok

Primary sources: support.microsoft.com · support.apple.com