Potok turns speech into text in 33 languages, including English and Russian.
Spokenly is voice input for macOS, Windows, Linux and iOS with an unusual model: local recognition models are free forever with no word limit, while cloud engines such as GPT-4o Transcribe need your own API key or a Pro subscription. Potok (potok.now) is simpler: ready-made cloud recognition with no keys or setup and a free limit of 2500 words per week.
Spokenly is voice input that gives you a choice rather than a ready solution: you can recognize speech for free right on the device, or you can connect a cloud engine such as Deepgram or GPT-4o Transcribe through your own API key. Such flexibility is unusual for voice input and requires a bit more figuring out than “install it and talk”. Here is how it works, who it suits and what to check before installing.
How Spokenly works
Spokenly has two fundamentally different ways of recognizing speech, and the choice between them is not a detail but the program's central feature. The first is the local Whisper and Parakeet models: they are installed on the device and recognize speech without an internet connection, for free and with no limit on the amount of dictation.
The second way is cloud engines: GPT-4o Transcribe, Deepgram Nova 3, Soniox and others. To use them, you need either your own API key from the chosen cloud service (BYOK, bring your own key) or a Spokenly Pro subscription, which gives access without setting up keys separately.
The own-key approach is unusual for an ordinary user: you need to create an account with a third-party recognition provider, get a key and paste it into Spokenly's settings. In return, you pay the provider directly for actual use, with no markup from Spokenly itself and no limits from the program's developer.
The program works on four platforms, macOS, Windows, Linux and iOS, which is rare among voice input tools: Linux support is found almost nowhere else. An overview of similar programs is in the section voice input software.
| Spokenly | Potok | |
|---|---|---|
| Platforms | Spokenly: macOS, Windows, Linux, iOS | Potok: Windows, macOS, Linux |
| Free | Spokenly: local models (Whisper/Parakeet) are free forever with no word limit; connecting your own API keys (BYOK) is also free | Potok: Free: 2500 words per week; full access for the first 14 days, no card needed |
| Price | Spokenly: $9.99/mo (Pro, monthly); $99.99/yr (Pro, yearly (≈$8.33/mo)) | Potok: Pro 690 ₽/mo, 499 ₽/mo when paid yearly |
| Payment from Russia | Spokenly: not disclosed | Potok: Russian bank cards, rubles |
| Where speech is recognized | Spokenly: hybrid: locally on the device (Whisper/Parakeet, free) or in the cloud (GPT-4o Transcribe, Deepgram Nova 3, Soniox and others, via BYOK or Pro) | Potok: cloud; internet required |
| Russian language | Spokenly: not disclosed | Potok: primary language |
| Company | Spokenly: not disclosed | Potok: Sole proprietor, Russia |
Sources: spokenly.app · spokenly.app
Who Spokenly suits
- those who understand technical details and are ready to connect a cloud service's API key themselves;
- Linux users, for whom voice input is a rarity in general;
- those who need free recognition with no word limit and without the internet: the local models cover this task completely;
- users who already use a specific cloud API for other tasks and want to use the same account for dictation;
- those who are ready to pay for a Pro subscription for convenience, without dealing with keys and setup;
- those who need to work on several systems at once: macOS, Windows, Linux and iOS in one tool.
What switching to dictation instead of typing looks like in general is in the article six months of voice input instead of the keyboard: an honest account (in Russian).
Limitations for a user in Russia
The legal entity that developed Spokenly is not stated on the website, and neither is whether the Pro subscription accepts Russian bank cards directly. Clarify this question separately before subscribing rather than take it for granted.
If you choose the own-API-key path, payment works in two layers: the Spokenly program itself may be free, but the recognition provider, OpenAI, Deepgram or another, bills separately under its own rules. Check the availability of payment for Russian users with each provider separately rather than assume that since the program itself charges nothing, there will be no payment issues at all.
There is no data on the quality of Russian speech recognition for either the local models or the cloud options: Spokenly's website does not publish a list of languages with details for each. Before relying on the program for Russian dictation, check the result on your own phrases; fortunately, the free local models let you do this at no cost.
| Service | Platforms | Free | Price | Payment from Russia | Where speech is recognized |
|---|---|---|---|---|---|
| Potok | Windows, macOS, Linux | Free: 2500 words per week; full access for the first 14 days, no card needed | Pro 690 ₽/mo, 499 ₽/mo when paid yearly | Russian bank cards, rubles | cloud, servers in Russia; internet required |
| Spokenly | macOS, Windows, Linux, iOS | local models (Whisper/Parakeet) are free forever with no word limit; connecting your own API keys (BYOK) is also free | $9.99/mo (Pro, monthly); $99.99/yr (Pro, yearly (≈$8.33/mo)) | not disclosed | hybrid: locally on the device (Whisper/Parakeet, free) or in the cloud (GPT-4o Transcribe, Deepgram Nova 3, Soniox and others, via BYOK or Pro) |
| Deepgram | API | Free $200 credit without a card, then pay as you go | $0.0043/minute (Nova-3 monolingual, batch, Pay As You Go); $0.0052/minute (Nova-3 multilingual, batch, Pay As You Go); $0.0048/minute (Whisper Large, batch) | not disclosed | not disclosed |
When Potok does not replace Spokenly
If fully local recognition without the internet and with no limit on volume matters to you, Potok does not offer it: Potok is a cloud service, recognition runs on servers in Russia, and it does not work without the internet.
Potok also lacks the flexibility of choosing a recognition engine: there is one model, its own, with no way to connect a third-party API key.
Frequently asked questions
No, if you use the local Whisper and Parakeet models: they are free and work without the internet and without keys. An API key or a Pro subscription is needed only for cloud engines such as GPT-4o Transcribe or Deepgram Nova 3.
Yes, Linux is one of the four supported platforms along with macOS, Windows and iOS. This is rare among voice input programs: most competitors have no Linux support.
What Spokenly is and how it works. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For What Spokenly is and how it works you dictate into the same field where you normally type, so there is no need to switch between apps.
What Spokenly is and how it works. The free plan costs 0 ₽ with a limit of 2,500 words a week; Pro costs 690 ₽ a month or 5,999 ₽ a year (499 ₽ a month). Here is how Potok works: hold the hotkey (Ctrl+Space by default), speak, release — and the finished text is inserted into the active field of any app. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For What Spokenly is and how it works you dictate into the same field where you normally type, so there is no need to switch between apps.
What Spokenly is and how it works. Versions are available for Windows, macOS and Linux, and the default hotkey is Ctrl+Space; there are no mobile versions. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. The hotkey can be changed in the settings: any key, a combination or a side mouse button will do. Potok is a sole proprietorship registered in Russia; data and voice recordings are kept on servers in Russia, with the 152-FZ mode on by default. For What Spokenly is and how it works you dictate into the same field where you normally type, so there is no need to switch between apps.
What Spokenly is and how it works. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For What Spokenly is and how it works you dictate into the same field where you normally type, so there is no need to switch between apps.
If you want to compare for yourself
Take one of your own tasks and dictate it in Potok. The first 14 days have no limits and need no card. Potok is a cloud service, so it does not work without the internet.
Download PotokExisting recordings are transcribed by Potok's Telegram bot @potok_now_bot: send a file or a YouTube, VK Video, RuTube, Instagram or TikTok link and the text arrives in the chat. The Potok subscription removes the limit in the bot too.
Primary sources: spokenly.app · spokenly.app