PixThru

Transcribe Ukrainian Audio to Text — Free, No Upload

Convert Ukrainian audio or video into Cyrillic text with і, ї, є and ґ, in your browser. 100% free, no per-minute limit, no account — nothing is uploaded.

Model
Spoken
Output
⬇️ One-time download: 104 MB (Accurate model 73 MB + 31 MB audio engine, shared with the video tools) — only the first time: it stays saved in your browser, so next time it starts right away. (Translating or switching model needs its own file; a browser can clear this cache if storage runs very low.) Processing takes about 4-8 min per 10 minutes of audio on a typical laptop.
What exactly is downloaded — and is it safe?
  • • The speech model is OpenAI's Whisper, open source, converted to run in browsers. The audio engine is FFmpeg, the open-source tool behind most video software.
  • • They come from Hugging Face and unpkg — public repositories used by researchers and developers worldwide, not from us.
  • • They are not programs. Nothing is installed, no permission is asked, and your browser keeps them in its own cache exactly like it keeps a website's images.
  • • They can't read your files or touch anything outside this page. Remove them any time by clearing this site's data in your browser.
  • • Your audio never goes the other way: this site has no server receiving files.

Drop your video or audio here or click to choose

transcribed on your device by OpenAI's Whisper — your recording is not uploaded

ℹ️ Use a recording on your device that you own or have permission to process. This tool cannot fetch YouTube or social video links. Start with a short clip. Larger models can improve accuracy but require more memory and download data. Processing time varies by device, model and recording length. Always review the result.

For Ukrainian the first requirement is that the transcript is Ukrainian: written with і, ї, є and ґ, with apostrophes where they belong, and not quietly converted into Russian because the two share an alphabet and a detector guessed wrong. This page removes that risk by opening with Ukrainian selected, so the Whisper model transcribes in Ukrainian from the first word.

Lectures, interviews, recorded calls, voice messages and news segments all transcribe well when the speech is clear, with proper names and place names spelled in their Ukrainian forms. Everything runs inside your browser: the model is downloaded once and the audio is processed on your own device, which for many people is the whole point, since a private conversation should not sit on a server anywhere. There is no fee per minute and no account. Plain text is the output, with SRT and VTT files when you need timestamps.

The honest limits: surzhyk and code-switching between Ukrainian and Russian come out as Ukrainian, so Russian phrases may be adapted or mangled, and you should pick whichever language dominates the recording. Background noise, music under a voice and several people talking at once reduce accuracy, as does distance from the microphone. Names, numbers and dates deserve a check against the audio, and a long file is faster on a laptop than on a phone.

More sizes & options

Frequently asked questions

Will it mistake Ukrainian for Russian?
Not on this page, which selects Ukrainian explicitly. Automatic detection elsewhere sometimes does, because the languages share the Cyrillic script.
What about surzhyk or mixed speech?
It is transcribed as Ukrainian, so Russian words may come out adapted. Choose the language that dominates the recording.
Can I get an English translation?
Yes. Set the output language to English and the translation is done in the same run, on your device.
Does it work on voice messages from messaging apps?
Yes, once saved as a file. Voice messages are compressed and often recorded in noisy places, so expect a few more errors than with a studio recording, but clear speech is captured well.
Will names and places be spelled the Ukrainian way?
Yes, because the language is fixed to Ukrainian, so Київ, Львів and Харків appear in Ukrainian orthography rather than Russian forms. Foreign names are transliterated by sound, so check unusual ones.

Guides

Related tools

🔒 Private mode (the default): your recording never leaves your device. Instant mode is optional, you switch it on yourself, and it sends the audio to the browser's speech service.