✳ FREE · NO UPLOAD · NO SIGN-UP · 99 LANGUAGES

Audio and video to text, free and private

Drop a recording, podcast, voice memo or video. OpenAI’s Whisper speech model runs on your own device and gives you an editable transcript with timestamps.

Public-domain LibriVox recording. Load it, then press Transcribe to try the full tool.

First use downloads the speech model and engine (about 97 MB, of which 72.5 MB is the model); later visits load it from your browser cache. Runs on your CPU; nothing is uploaded. Up to 100 MB and 2 hours per file; under 30 minutes is the comfortable range on a laptop.

To transcribe audio or video for free without uploading it, drop the file above: Whisper base runs inside your browser, detects the language, and returns an editable transcript with timestamps as TXT, SRT or VTT. Accuracy depends on the language: about 9% word errors for English and Spanish in the Whisper paper, far worse for some.

Checked by Koldflux · updated 2026-09-25 · accuracy figures read from the Whisper paper’s tables; tool tested on public-domain recordings

What the free tool runs

Detail
ModelWhisper base (OpenAI), multilingual, 74M parameters; ONNX export by onnx-community, MIT-licensed weights
DownloadAbout 97 MB on first use (72.5 MB model + ONNX Runtime WebAssembly engine), then cached by your browser
Languages99 language settings, plus automatic detection from the first speech
OutputEditable transcript with timestamps; TXT, SRT and VTT downloads; English translation option
FilesMP3, M4A, WAV, OGG, Opus, FLAC, AAC, MP4, MOV, WebM, MKV and most other audio or video your browser or ffmpeg can open; up to 100 MB
PrivacyAudio is processed in your browser tab and never uploaded
Sources: onnx-community/whisper-base (the files this tool runs) (checked 2026-09-25) · openai/whisper README (checked 2026-09-25) · Transformers.js (checked 2026-09-25)

Accuracy by language

Word error rate on the FLEURS read-speech test in the Whisper paper (lower is better). For Chinese and Japanese it is effectively a character error rate. The free tool runs Whisper base; large-v2 is the largest model the paper measures.

LanguageWhisper base (this tool)VerdictWhisper large-v2Verdict
English8.9%Good4.2%Good
Spanish9.9%Good3%Good
Portuguese13%Good4.3%Good
Italian17.9%Usable, needs a proofread4%Good
German17.9%Usable, needs a proofread4.5%Good
Russian20.5%Usable, needs a proofread5.6%Good
Japanese22.8% (CER)Usable, needs a proofread5.3%Good
Korean27.8%Usable, needs a proofread14.3%Good
French28.5%Usable, needs a proofread8.3%Good
Turkish27.5%Usable, needs a proofread8.4%Good
Polish30.8%Rough draft only5.4%Good
Dutch33%Rough draft only6.7%Good
Chinese34.1% (CER)Rough draft only14.7%Good
Indonesian33.1%Rough draft only7.1%Good
Vietnamese40.5%Rough draft only10.3%Good
Arabic48.8%Rough draft only16%Usable, needs a proofread
Ukrainian37.7%Rough draft only8.6%Good
Urdu52%Rough draft only22.6%Usable, needs a proofread
Tamil58.7%Rough draft only17.5%Usable, needs a proofread
Hebrew61.7%Not reliable27.1%Usable, needs a proofread
Hindi101.1%Not reliable21.5%Usable, needs a proofread
Marathi100.3%Not reliable38.3%Rough draft only
Bengali100.6%Not reliable104.1%Not reliable
Telugu105.2%Not reliable99%Not reliable
Kannada107.2%Not reliable37%Rough draft only
Malayalam107.4%Not reliable100.7%Not reliable
Gujarati101.4%Not reliable102.7%Not reliable

How it runs on your device

The page reads the audio track with your browser’s own decoder (ffmpeg.wasm steps in for formats the browser cannot open), mixes it to mono and resamples it to 16 kHz, the input Whisper expects. Long recordings are cut into windows of at most 30 seconds, the length Whisper was trained on, and each cut is placed at the quietest moment between 20 and 30 seconds so words are not split. Silent windows are skipped, because Whisper tends to invent text on silence.

The model is Whisper base, OpenAI’s 74-million-parameter multilingual model, run by Transformers.js in a background worker: a 4-bit encoder that uses your graphics card through WebGPU when available, and an 8-bit decoder on the CPU. If Whisper starts repeating itself, which small models do, that window is decoded again with fallback settings, the same idea as the original Whisper software. The first run downloads about 97 MB (the model is 72.5 MB); after that it loads from your browser’s cache.

How to transcribe a file

  1. Drop the fileAny audio or video up to 100 MB. It stays on your device.
  2. Pick the language, or let it detectAuto-detect listens to the first speech. For mixed-language talk or closely related languages, choose it yourself.
  3. Transcribe and correctText appears window by window. Click a timestamp to hear that part, and fix words in place.
  4. DownloadTXT for notes and scripts, SRT or VTT for subtitles. Your edits are in every file.

Limits and when to use something else

Frequently asked questions

Is it really free, with no sign-up?

Yes. The speech model runs on your own device, so there is no server cost per minute: no account, no watermark, no daily limit. Files up to 100 MB and 2 hours.

Is my file uploaded anywhere?

No. The audio is decoded and transcribed inside your browser tab. The only downloads are the model and engine files, once, which your browser then caches.

How accurate is it?

It depends on the language. The Whisper paper measures this model (Whisper base) at 8.9% word errors for English and 9.9% for Spanish on read speech, around 18 to 30% for German, Japanese and French, and 100% or worse for several Indian languages. The table on this page lists each language.

How long does it take?

On one CPU thread of our test server, 30 seconds of English took about 6 seconds. Laptops vary; with WebGPU the heavy part runs on the graphics card. A 30-minute file is comfortable; long files mostly need patience and a tab left open.

Does it label speakers?

No. Whisper produces one stream of text with timestamps. If you need speaker names, add them while editing.

Can I paste a YouTube or TikTok link?

No. The tool works on files on your device. Download your own video first, then drop the file.

Can I record from my microphone?

Not on this site: microphone access is switched off for all Koldflux pages. Record with your phone or computer’s recorder app and drop the file.

Language pages

Each page has the tool preset to that language, measured accuracy, our own test on a real recording and subtitle rules.

FROM TRANSCRIPT TO POSTS

Turn one idea into a week of posts

Koldflux Studio (paid, from $19/month) transcribes your upload on our servers with Whisper large-v3-turbo and automatic language detection, then turns one recording into Shorts and carousel posts you review, approve and export. It does not publish or schedule for you.

  1. 1 · Recording, idea or script
  2. 2 · Pick the angles
  3. 3 · Review and approve
  4. 4 · Export Shorts and carousels
Turn a recording into posts
Koldflux Studio: choosing which angles (Opportunities) to turn into Shorts before anything is generated
Koldflux Studio: you choose the angles before anything is made.